diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..239382604dad572eccb4e295b57cbca0dd7ef99d --- /dev/null +++ b/README.md @@ -0,0 +1,152 @@ +# INTELLECT-3-V + +A vision-language model created by grafting the language model weights from [INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3) into the [GLM-4.6V](https://huggingface.co/THUDM/GLM-4.6V) architecture. + +## Motivation + +INTELLECT-3 is a strong open-source language model, but lacks vision capabilities. GLM-4.6V is a vision-language model with an identical language model architecture. By replacing GLM-4.6V's language model weights with INTELLECT-3's weights while preserving the vision encoder and projection layers, we create a vision-language model powered by INTELLECT-3. + +## Architecture + +Both models share the same language model backbone: +- 46 transformer layers (layer 0 is dense MLP, layers 1-45 are MoE) +- 4096 hidden dimension +- 128 routed experts + shared experts per MoE layer +- Grouped Query Attention (12288 q_proj, 1024 k/v_proj) +- 151552 vocabulary size +- BF16 weights + +GLM-4.6V additionally includes: +- 24-layer vision transformer (1536 hidden dim) +- Visual merger projecting vision features to LLM hidden dimension +- Downsampling convolution for spatial compression + +## What Was Grafted + +The following weights were copied from INTELLECT-3 to GLM-4.6V: + +| INTELLECT-3 | GLM-4.6V | +|-------------|----------| +| `model.layers.*` | `model.language_model.layers.*` | +| `model.norm.weight` | `model.language_model.norm.weight` | + +## What Was Preserved (from GLM-4.6V) + +- `model.language_model.embed_tokens.weight` — kept to maintain vision token compatibility +- `lm_head.weight` — kept aligned with embed_tokens +- `model.visual.*` — entire vision encoder and merger preserved + +## Rationale + +**Why replace the final norm?** The RMSNorm after the last transformer layer is tightly coupled to the layer outputs it normalizes. INTELLECT-3's norm was trained end-to-end with its layers and learned to normalize their specific output distribution. + +**Why keep embed_tokens?** The vision merger projects visual features into the same embedding space as text tokens. Replacing embed_tokens could break the alignment between text and vision embeddings. Additionally, lm_head is often tied or co-trained with embed_tokens. + +**Why not replace lm_head?** Same reasoning — keeping lm_head and embed_tokens together maintains their learned relationship. + +## Known Limitations + +1. **Embedding space mismatch**: INTELLECT-3's layers learned representations in a potentially different embedding space than GLM-4.6V. This may cause some degradation in both language and vision-language performance. + +2. **Vision-language alignment**: The visual merger was trained to project into GLM-4.6V's representation space. INTELLECT-3 may have learned different internal representations, potentially affecting vision-language tasks. + +3. **Tokenizer compatibility**: While both models have the same vocabulary size (151552), verify tokenizer compatibility for your use case. + +## Creation Script + +The model was created using `graft_intellect3_to_glm.py`: + +```bash +python graft_intellect3_to_glm.py \ + --intellect3 ~/models/INTELLECT-3 \ + --glm ~/models/GLM-4.6V \ + --output ~/models/INTELLECT-3-V +``` + +## Source Model Architectures + +### INTELLECT-3 + +``` +lm_head.weight,[151552,4096],BF16 +model.embed_tokens.weight,[151552,4096],BF16 +model.layers.0.mlp.down_proj.weight,[4096,10944],BF16 +model.layers.0.mlp.gate_proj.weight,[10944,4096],BF16 +model.layers.0.mlp.up_proj.weight,[10944,4096],BF16 +model.layers.[0-45].input_layernorm.weight,[4096],BF16 +model.layers.[0-45].post_attention_layernorm.weight,[4096],BF16 +model.layers.[0-45].self_attn.k_proj.bias,[1024],BF16 +model.layers.[0-45].self_attn.k_proj.weight,[1024,4096],BF16 +model.layers.[0-45].self_attn.o_proj.weight,[4096,12288],BF16 +model.layers.[0-45].self_attn.q_proj.bias,[12288],BF16 +model.layers.[0-45].self_attn.q_proj.weight,[12288,4096],BF16 +model.layers.[0-45].self_attn.v_proj.bias,[1024],BF16 +model.layers.[0-45].self_attn.v_proj.weight,[1024,4096],BF16 +model.layers.[1-45].mlp.experts.[0-127].down_proj.weight,[4096,1408],BF16 +model.layers.[1-45].mlp.experts.[0-127].gate_proj.weight,[1408,4096],BF16 +model.layers.[1-45].mlp.experts.[0-127].up_proj.weight,[1408,4096],BF16 +model.layers.[1-45].mlp.gate.e_score_correction_bias,[128],F32 +model.layers.[1-45].mlp.gate.weight,[128,4096],BF16 +model.layers.[1-45].mlp.shared_experts.down_proj.weight,[4096,1408],BF16 +model.layers.[1-45].mlp.shared_experts.gate_proj.weight,[1408,4096],BF16 +model.layers.[1-45].mlp.shared_experts.up_proj.weight,[1408,4096],BF16 +model.norm.weight,[4096],BF16 +``` + +### GLM-4.6V + +``` +lm_head.weight,[151552,4096],BF16 +model.language_model.embed_tokens.weight,[151552,4096],BF16 +model.language_model.layers.0.mlp.down_proj.weight,[4096,10944],BF16 +model.language_model.layers.0.mlp.gate_proj.weight,[10944,4096],BF16 +model.language_model.layers.0.mlp.up_proj.weight,[10944,4096],BF16 +model.language_model.layers.[0-45].input_layernorm.weight,[4096],BF16 +model.language_model.layers.[0-45].post_attention_layernorm.weight,[4096],BF16 +model.language_model.layers.[0-45].self_attn.k_proj.bias,[1024],BF16 +model.language_model.layers.[0-45].self_attn.k_proj.weight,[1024,4096],BF16 +model.language_model.layers.[0-45].self_attn.o_proj.weight,[4096,12288],BF16 +model.language_model.layers.[0-45].self_attn.q_proj.bias,[12288],BF16 +model.language_model.layers.[0-45].self_attn.q_proj.weight,[12288,4096],BF16 +model.language_model.layers.[0-45].self_attn.v_proj.bias,[1024],BF16 +model.language_model.layers.[0-45].self_attn.v_proj.weight,[1024,4096],BF16 +model.language_model.layers.[1-45].mlp.experts.[0-127].down_proj.weight,[4096,1408],BF16 +model.language_model.layers.[1-45].mlp.experts.[0-127].gate_proj.weight,[1408,4096],BF16 +model.language_model.layers.[1-45].mlp.experts.[0-127].up_proj.weight,[1408,4096],BF16 +model.language_model.layers.[1-45].mlp.gate.e_score_correction_bias,[128],F32 +model.language_model.layers.[1-45].mlp.gate.weight,[128,4096],BF16 +model.language_model.layers.[1-45].mlp.shared_experts.down_proj.weight,[4096,1408],BF16 +model.language_model.layers.[1-45].mlp.shared_experts.gate_proj.weight,[1408,4096],BF16 +model.language_model.layers.[1-45].mlp.shared_experts.up_proj.weight,[1408,4096],BF16 +model.language_model.norm.weight,[4096],BF16 +model.visual.blocks.[0-23].attn.proj.weight,[1536,1536],BF16 +model.visual.blocks.[0-23].attn.qkv.weight,[4608,1536],BF16 +model.visual.blocks.[0-23].mlp.down_proj.weight,[1536,4096],BF16 +model.visual.blocks.[0-23].mlp.gate_proj.weight,[4096,1536],BF16 +model.visual.blocks.[0-23].mlp.up_proj.weight,[4096,1536],BF16 +model.visual.blocks.[0-23].norm[1-2].weight,[1536],BF16 +model.visual.downsample.bias,[4096],BF16 +model.visual.downsample.weight,[4096,1536,2,2],BF16 +model.visual.embeddings.position_embedding.weight,[576,1536],BF16 +model.visual.merger.down_proj.weight,[4096,10944],BF16 +model.visual.merger.gate_proj.weight,[10944,4096],BF16 +model.visual.merger.post_projection_norm.bias,[4096],BF16 +model.visual.merger.post_projection_norm.weight,[4096],BF16 +model.visual.merger.proj.weight,[4096,4096],BF16 +model.visual.merger.up_proj.weight,[10944,4096],BF16 +model.visual.patch_embed.proj.bias,[1536],BF16 +model.visual.patch_embed.proj.weight,[1536,3,2,14,14],BF16 +model.visual.post_conv_layernorm.weight,[1536],BF16 +model.visual.post_layernorm.weight,[1536],BF16 +``` + +## License + +Please refer to the licenses of the source models: +- [INTELLECT-3 License](https://huggingface.co/PrimeIntellect/INTELLECT-3) +- [GLM-4.6V License](https://huggingface.co/THUDM/GLM-4.6V) + +## Acknowledgments + +- [Prime Intellect](https://www.primeintellect.ai/) for INTELLECT-3 +- [THUDM](https://github.com/THUDM) for GLM-4.6V \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..fe090a3bdbf2c94081d5b72bb0fb15305d1e2b99 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,141 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%} + <|begin_of_image|><|image|><|end_of_image|> + {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%} + <|begin_of_video|><|video|><|end_of_video|> + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{% if m.content is string %} +{{ m.content }} +{%- else %} +{%- for item in m.content %} +{% if item.type == 'video' or 'video' in item %} +<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %} +<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %} +{{ item.text }} +{%- endif %} +{%- endfor %} +{%- endif %} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{% elif m.content is iterable and m.content is not mapping %} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} +{{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{%- for tr in m.content -%} + {%- if tr is mapping and tr.type is defined -%} + {%- set t = tr.type | lower -%} + {%- if t == 'text' and tr.text is defined -%} +{{ tr.text }} + {%- elif t in ['image', 'image_url'] -%} +<|begin_of_image|><|image|><|end_of_image|> + {%- elif t in ['video', 'video_url'] -%} +<|begin_of_video|><|video|><|end_of_video|> + {%- else -%} +{{ tr | tojson(ensure_ascii=False) }} + {%- endif -%} + {%- else -%} +{{ tr.output if tr.output is defined else tr }} + {%- endif -%} +{%- endfor -%} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{# ====== 逻辑结束 ====== #} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} +<|assistant|> +{{'\n' if (enable_thinking is defined and not enable_thinking) else ''}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0a0f7ade6dc6360133602b23a1396ba887cb4b31 --- /dev/null +++ b/config.json @@ -0,0 +1,80 @@ +{ + "architectures": [ + "Glm4vMoeForConditionalGeneration" + ], + "model_type": "glm4v_moe", + "text_config": { + "attention_bias": true, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4v_moe_text", + "moe_intermediate_size": 1408, + "n_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 0, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "qk_layernorm": false, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "mrope_section": [ + 8, + 12, + 12 + ], + "partial_rotary_factor": 0.5, + "rope_theta": 500000, + "rope_type": "default" + }, + "routed_scaling_factor": 1.0, + "topk_group": 1, + "use_cache": true, + "use_qk_norm": false, + "vocab_size": 151552 + }, + "tie_word_embeddings": false, + "transformers_version": "5.0.0rc0", + "image_start_token_id": 151339, + "image_end_token_id": 151340, + "video_start_token_id": 151341, + "video_end_token_id": 151342, + "image_token_id": 151363, + "video_token_id": 151364, + "vision_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "depth": 24, + "hidden_act": "silu", + "hidden_dropout_prob": 0.0, + "hidden_size": 1536, + "image_size": 336, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 10944, + "model_type": "glm4v_moe_vision", + "num_heads": 12, + "out_hidden_size": 4096, + "patch_size": 14, + "rms_norm_eps": 1e-05, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + } +} diff --git a/convert.py b/convert.py new file mode 100644 index 0000000000000000000000000000000000000000..b6947d2e28c67b5bc53d13755460fae498698408 --- /dev/null +++ b/convert.py @@ -0,0 +1,259 @@ +#!/usr/bin/env python3 +""" +Graft INTELLECT-3 language model weights into GLM-4.6V vision-language model. + +This script: +1. Loads both models into CPU memory +2. Copies model.layers.* from INTELLECT-3 to model.language_model.layers.* in GLM-4.6V +3. Copies model.norm.weight from INTELLECT-3 to model.language_model.norm.weight in GLM-4.6V +4. Saves the resulting model to a new directory + +Does NOT touch: +- model.language_model.embed_tokens (needed for vision token compatibility) +- lm_head (kept aligned with embed_tokens) +- model.visual.* (vision encoder preserved) +""" + +import os +import argparse +import json +import shutil +from pathlib import Path +from safetensors import safe_open +from safetensors.torch import save_file +import torch +from tqdm import tqdm + + +def get_safetensor_files(model_dir: Path) -> list[Path]: + """Get all safetensor files in a model directory.""" + files = sorted(model_dir.glob("*.safetensors")) + if not files: + raise FileNotFoundError(f"No safetensor files found in {model_dir}") + return files + + +def load_state_dict_from_safetensors(model_dir: Path) -> dict[str, torch.Tensor]: + """Load all tensors from safetensor files into a state dict.""" + state_dict = {} + files = get_safetensor_files(model_dir) + + for f in tqdm(files, desc=f"Loading {model_dir.name}"): + with safe_open(f, framework="pt", device="cpu") as st: + for key in st.keys(): + state_dict[key] = st.get_tensor(key) + + return state_dict + + +def graft_weights( + intellect3_state: dict[str, torch.Tensor], + glm_state: dict[str, torch.Tensor] +) -> dict[str, torch.Tensor]: + """ + Graft INTELLECT-3 weights into GLM-4.6V state dict. + + Mapping: + - model.layers.* -> model.language_model.layers.* + - model.norm.weight -> model.language_model.norm.weight + """ + grafted_state = dict(glm_state) # shallow copy + + grafted_count = 0 + skipped_keys = [] + + for intellect_key, tensor in tqdm(intellect3_state.items(), desc="Grafting weights"): + # Skip embed_tokens and lm_head from INTELLECT-3 + if "embed_tokens" in intellect_key or "lm_head" in intellect_key: + skipped_keys.append(intellect_key) + continue + + # Map model.layers.* -> model.language_model.layers.* + if intellect_key.startswith("model.layers."): + glm_key = intellect_key.replace("model.layers.", "model.language_model.layers.") + # Map model.norm.weight -> model.language_model.norm.weight + elif intellect_key == "model.norm.weight": + glm_key = "model.language_model.norm.weight" + else: + skipped_keys.append(intellect_key) + continue + + # Verify the key exists in GLM and shapes match + if glm_key not in grafted_state: + print(f"WARNING: {glm_key} not found in GLM-4.6V state dict!") + continue + + if grafted_state[glm_key].shape != tensor.shape: + print(f"WARNING: Shape mismatch for {glm_key}:") + print(f" INTELLECT-3: {tensor.shape}") + print(f" GLM-4.6V: {grafted_state[glm_key].shape}") + continue + + grafted_state[glm_key] = tensor + grafted_count += 1 + + print(f"\nGrafted {grafted_count} tensors from INTELLECT-3") + print(f"Skipped {len(skipped_keys)} tensors: {skipped_keys[:5]}{'...' if len(skipped_keys) > 5 else ''}") + + return grafted_state + + +def save_state_dict_to_safetensors( + state_dict: dict[str, torch.Tensor], + output_dir: Path, + max_shard_size: int = 5 * 1024 ** 3 # 5GB default +): + """Save state dict to sharded safetensor files.""" + output_dir.mkdir(parents=True, exist_ok=True) + + # Calculate total size and plan shards + tensors_by_size = [(k, v, v.numel() * v.element_size()) for k, v in state_dict.items()] + total_size = sum(size for _, _, size in tensors_by_size) + + print(f"\nTotal model size: {total_size / 1024**3:.2f} GB") + + # Create shards + shards = [] + current_shard = {} + current_size = 0 + + for key, tensor, size in tensors_by_size: + if current_size + size > max_shard_size and current_shard: + shards.append(current_shard) + current_shard = {} + current_size = 0 + + current_shard[key] = tensor + current_size += size + + if current_shard: + shards.append(current_shard) + + print(f"Saving to {len(shards)} shard(s)...") + + # Save shards and build index + weight_map = {} + + for i, shard in enumerate(tqdm(shards, desc="Saving shards")): + if len(shards) == 1: + filename = "model.safetensors" + else: + filename = f"model-{i+1:05d}-of-{len(shards):05d}.safetensors" + + filepath = output_dir / filename + save_file(shard, filepath) + + for key in shard.keys(): + weight_map[key] = filename + + # Save index if sharded + if len(shards) > 1: + index = { + "metadata": {"total_size": total_size}, + "weight_map": weight_map + } + with open(output_dir / "model.safetensors.index.json", "w") as f: + json.dump(index, f, indent=2) + + return weight_map + + +def copy_config_files(src_dir: Path, dst_dir: Path): + """Copy config files from source to destination.""" + config_files = [ + "config.json", + "tokenizer.json", + "tokenizer_config.json", + "special_tokens_map.json", + "generation_config.json", + "preprocessor_config.json", + "chat_template.json", + ] + + for filename in config_files: + src_file = src_dir / filename + if src_file.exists(): + shutil.copy2(src_file, dst_dir / filename) + print(f"Copied {filename}") + + +def main(): + parser = argparse.ArgumentParser( + description="Graft INTELLECT-3 weights into GLM-4.6V" + ) + parser.add_argument( + "--intellect3", + type=Path, + default=Path.home() / "models" / "INTELLECT-3", + help="Path to INTELLECT-3 model directory" + ) + parser.add_argument( + "--glm", + type=Path, + default=Path.home() / "models" / "GLM-4.6V", + help="Path to GLM-4.6V model directory" + ) + parser.add_argument( + "--output", + type=Path, + default=Path.home() / "models" / "INTELLECT-3-V", + help="Path to output directory" + ) + parser.add_argument( + "--shard-size", + type=int, + default=5, + help="Maximum shard size in GB (default: 5)" + ) + + args = parser.parse_args() + + print("=" * 60) + print("INTELLECT-3 -> GLM-4.6V Weight Grafting") + print("=" * 60) + print(f"INTELLECT-3 source: {args.intellect3}") + print(f"GLM-4.6V source: {args.glm}") + print(f"Output directory: {args.output}") + print("=" * 60) + + # Verify source directories exist + if not args.intellect3.exists(): + raise FileNotFoundError(f"INTELLECT-3 directory not found: {args.intellect3}") + if not args.glm.exists(): + raise FileNotFoundError(f"GLM-4.6V directory not found: {args.glm}") + + # Load both models + print("\nStep 1: Loading models into CPU memory...") + intellect3_state = load_state_dict_from_safetensors(args.intellect3) + glm_state = load_state_dict_from_safetensors(args.glm) + + print(f"\nINTELLECT-3 tensors: {len(intellect3_state)}") + print(f"GLM-4.6V tensors: {len(glm_state)}") + + # Graft weights + print("\nStep 2: Grafting INTELLECT-3 weights into GLM-4.6V...") + grafted_state = graft_weights(intellect3_state, glm_state) + + # Free memory from source models + del intellect3_state + del glm_state + + # Save grafted model + print("\nStep 3: Saving grafted model...") + save_state_dict_to_safetensors( + grafted_state, + args.output, + max_shard_size=args.shard_size * 1024 ** 3 + ) + + # Copy config files from GLM-4.6V (since we're keeping its architecture) + print("\nStep 4: Copying config files from GLM-4.6V...") + copy_config_files(args.glm, args.output) + + print("\n" + "=" * 60) + print("Done! Grafted model saved to:", args.output) + print("=" * 60) + + +if __name__ == "__main__": + main() diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..00e2636f2d875aca6c6f12dfa3d23f0a364d337f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "_from_model_config": true, + "do_sample": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "top_p": 0.6, + "temperature": 0.8, + "top_k": 2, + "transformers_version": "5.0.0rc0" +} diff --git a/model-00002-of-00041.safetensors b/model-00002-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f9e83cb9a3e7277458f8c6ce1bd393ca8c0cded --- /dev/null +++ b/model-00002-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e16916549c3f2c5beaaa8ce76c48a73260af7e0a019ea96adbbe3ffca2923b +size 5363575312 diff --git a/model-00003-of-00041.safetensors b/model-00003-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c48e8336592ca20d03dac24d8df35511491bb8a --- /dev/null +++ b/model-00003-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294d4ade39bb96ef966cc241c190b17bff37210a1dd6ea41a53620c598214309 +size 5363619592 diff --git a/model-00004-of-00041.safetensors b/model-00004-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb25dc8772ebec8bf464ba9a83f2538f1ec67c55 --- /dev/null +++ b/model-00004-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070a9a69f9cceeb0514e07e565c0bca22ef02412b5ea67083470df9d9f862f02 +size 5363575224 diff --git a/model-00005-of-00041.safetensors b/model-00005-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86c5341201b24508c0b6c70ca0a602d34593662a --- /dev/null +++ b/model-00005-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6c7badf80f149045fd76946a03c4e152b1a9490606bde43b0e478249752e41 +size 5363575224 diff --git a/model-00006-of-00041.safetensors b/model-00006-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b3ee84e7f1a9229214a7bded2ba592ff072809a --- /dev/null +++ b/model-00006-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ae1a55c7a4f08899c926f2dc69ca09cbec5c0ee5066d043eb8df36a5b6d544 +size 5363575224 diff --git a/model-00007-of-00041.safetensors b/model-00007-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b3db05143901487e51e312007b0fef666520f195 --- /dev/null +++ b/model-00007-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d57281997daedd2cd8bfb64bef13d01fc48fa69d8ae627d35d0dece2803704a +size 5363575272 diff --git a/model-00008-of-00041.safetensors b/model-00008-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fbfe44ecd04e00d8631cd2251fbffbc46f17c410 --- /dev/null +++ b/model-00008-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acb579063d3e0aef416c935469aeeb4ef71121bbddf65c75bcfd04b5186b902d +size 5363566960 diff --git a/model-00009-of-00041.safetensors b/model-00009-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e5b031eedd61e5540d5b8b9a9689ff2a9c90e5c --- /dev/null +++ b/model-00009-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5537541ed849d1aec5a03ba3f6fbd412420ecc123baf6407392ebf9ec79a1778 +size 5363583992 diff --git a/model-00010-of-00041.safetensors b/model-00010-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..465c0a515caccb183f2b726f042c798755e928eb --- /dev/null +++ b/model-00010-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:910065ed4f943bde57e99b614995a025d22083f9dba9e74a78f5b0b08cf613a5 +size 5363620024 diff --git a/model-00011-of-00041.safetensors b/model-00011-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..288d5f12301a9535f2f31fc0d74fc41541870a8e --- /dev/null +++ b/model-00011-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d068184dedf2e75febd4500f7dbac3c304da64a916a5504325055bbb0db36b +size 5363575680 diff --git a/model-00012-of-00041.safetensors b/model-00012-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab8734245e1418f50f3de1af22f02e9232bb872a --- /dev/null +++ b/model-00012-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e8f7bb30f6f67beea4a9c046f2757ea9b6063a3e43c9751be12300caf4acac +size 5363575680 diff --git a/model-00013-of-00041.safetensors b/model-00013-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ba94e42e0615851dd9f8d27cb97cd1f1d2b9af5 --- /dev/null +++ b/model-00013-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05c10ffd6afdce59491acbae09d8d6276210aca5aef1f6e7a54bcc48aa15750 +size 5363575688 diff --git a/model-00014-of-00041.safetensors b/model-00014-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10377afb5ab48b009cd51b460a777557cd970613 --- /dev/null +++ b/model-00014-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92ae88cb4cec2c5edae04e7a8ba515892131b9294e212d3e5297c6e7e6a3e56 +size 5363575728 diff --git a/model-00015-of-00041.safetensors b/model-00015-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acc6cd580b73877e7765936fa1f56c4bca475840 --- /dev/null +++ b/model-00015-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd86d501d81c538c6215c096318a4d0813ac149eacf6b8dc32384ed3a6580fc +size 5363575736 diff --git a/model-00016-of-00041.safetensors b/model-00016-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..008abf94185a384d69900ed4ee00b6c0a5f48ab1 --- /dev/null +++ b/model-00016-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e53b380fdb8442cf5199a8d099fbf633f7cc201030c4cbbec7a24e76636687 +size 5361489896 diff --git a/model-00017-of-00041.safetensors b/model-00017-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59badc3b986e31dc2a60320d14ebe0f1697ceec6 --- /dev/null +++ b/model-00017-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd04e94143cc3ab4959e7be4e99b725dcd6dfb6be448d5a71827ede6434e7ce +size 5365705936 diff --git a/model-00018-of-00041.safetensors b/model-00018-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f7733bce136c805bb24addf50bd904ea45d6930 --- /dev/null +++ b/model-00018-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34921251b4117d709f9b870def609c06a0ee19a947591326740846f3e395c29a +size 5363575680 diff --git a/model-00019-of-00041.safetensors b/model-00019-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dae4c21ae09c8035957132b1d47837a9bad1f726 --- /dev/null +++ b/model-00019-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfac271a321ffdf71f18339d68ca9a963b561e66482939d27037b037b6f591e7 +size 5363575680 diff --git a/model-00020-of-00041.safetensors b/model-00020-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0607c48f109c97974d070c1eb7cda4ab0bfe4af9 --- /dev/null +++ b/model-00020-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc665d4223264593cdfb236f9983d35cbfb8d22b75659cfd70cf812392fa1560 +size 5363575696 diff --git a/model-00021-of-00041.safetensors b/model-00021-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..434331ed7516196a37f9625ebaea5d55de6d8c48 --- /dev/null +++ b/model-00021-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e24a876ca2551d8f26bcbde6ab69eb0912b7d381c3d7032c44c85780c49c3ce8 +size 5363575736 diff --git a/model-00022-of-00041.safetensors b/model-00022-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23028c74ad0f20d36f87b77ca47f0c490c6bee9a --- /dev/null +++ b/model-00022-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe3b04644e856b30b50fd58f821458166b65807962d8d8afbd9789b063b96c8 +size 5363575736 diff --git a/model-00023-of-00041.safetensors b/model-00023-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5266d1e118e4a2183e36e7df9e9062e1516915e7 --- /dev/null +++ b/model-00023-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294316579802e473bc9067b5d63ff3e3c3336b2601fba86b0fcbc32a61dfca6d +size 5280748552 diff --git a/model-00024-of-00041.safetensors b/model-00024-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1399be575c46320e5d3af6f19a498b93fa7b4dc --- /dev/null +++ b/model-00024-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbe67f9fe5867bd046d7952f035ea4a317695427ed09732da863a49f10f120f +size 5365705928 diff --git a/model-00025-of-00041.safetensors b/model-00025-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1e1f56340d2134521b9efffeea90d788621fefc --- /dev/null +++ b/model-00025-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c550e04a34e8996ff55eb04e5f07131dbeeeda8b6ce8c261262b3bf010ac6ee +size 5363575680 diff --git a/model-00026-of-00041.safetensors b/model-00026-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a17869249879096016345586f1b5986ee10351ae --- /dev/null +++ b/model-00026-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51242ebda76d87c6b6554e89646efe52d5378c9c4151ccaa5682b241114f892a +size 5363575680 diff --git a/model-00027-of-00041.safetensors b/model-00027-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4bc69bbbaf9204a591ca885b5523e0ec1435fabd --- /dev/null +++ b/model-00027-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ba10028421f788dd6bda5f923a7070a14da5ca94829e851eff5eec8e63d750 +size 5363575696 diff --git a/model-00028-of-00041.safetensors b/model-00028-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44348f57bb04c792b9e8ff2a2ec8f97462f3234d --- /dev/null +++ b/model-00028-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2465c61939b44de2a1c01e813784b1f5ed13174a31482e9ef27173d7c956cdf0 +size 5363575728 diff --git a/model-00029-of-00041.safetensors b/model-00029-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6a425a195456a3b261257a192ff01899ebcf9fb --- /dev/null +++ b/model-00029-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8a9fe785fe86f299c3fd9a54c708eb3f7bb26c63f9ad15761776d23d6cf3c9 +size 5363575736 diff --git a/model-00030-of-00041.safetensors b/model-00030-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19c72fbf4150359f376d246a9a39e221753b6039 --- /dev/null +++ b/model-00030-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f3d581024b5782391e7a848ab952e663a59ce93c62df55f9209e58e270b214 +size 5361478264 diff --git a/model-00031-of-00041.safetensors b/model-00031-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f031571f6d01b3ba8c220a8963de2d2ae04c847 --- /dev/null +++ b/model-00031-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ab10f73490a4d676b90eb06ea7b402fbbc8145c9cc3de9f2b2170b5b8a4739 +size 5365717520 diff --git a/model-00032-of-00041.safetensors b/model-00032-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd6ff435ba6b71c03f3820d93ac0b3bc6f9b7b5c --- /dev/null +++ b/model-00032-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a222975edd317613a379b812f92d05ee00bb414af3fda0437ab0474ddc1c617 +size 5363575680 diff --git a/model-00033-of-00041.safetensors b/model-00033-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..014f523016d54b12802513318726c4b239d36f64 --- /dev/null +++ b/model-00033-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f02049b5ce95890500ce992b9cd75282e89e5ad276d5c1f6999336d4794eabf +size 5363575680 diff --git a/model-00034-of-00041.safetensors b/model-00034-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d490794e8777cd5ea2689c1fd142fa74947a4af4 --- /dev/null +++ b/model-00034-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088a6843e5334436c9f85679a029b4b471f6f1b85238175b59bce1d27bf43cdb +size 5363575704 diff --git a/model-00035-of-00041.safetensors b/model-00035-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21b736bcc6f4d94e6a117f4c0169bc3de34c2ca2 --- /dev/null +++ b/model-00035-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194df5d2ce09178c02104cc3a23823b739c458b7b9504b389461ce45f6f661e3 +size 5363575728 diff --git a/model-00036-of-00041.safetensors b/model-00036-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..465e07f5e1a33bef17d7b23679caade79d934e9b --- /dev/null +++ b/model-00036-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5dee2d30f392e6ebe05c3569d12f3dacf3bf3b71c2e0c0ab130a1d1fe1e36e +size 5363575736 diff --git a/model-00037-of-00041.safetensors b/model-00037-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb929794446b5b7b214d9576d88ac3dc74b71c44 --- /dev/null +++ b/model-00037-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220dd8e4c825621a54251220ffa87d02080cd4e0955b29dcc61f050643778f38 +size 5309059384 diff --git a/model-00039-of-00041.safetensors b/model-00039-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90b38f42d0c14a39fe1a905d5b9a759752475b3e --- /dev/null +++ b/model-00039-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e9c3446f8a3d34e9f7112e72532fa026d52738376269862db7c93ab5e1eb76 +size 5363567360 diff --git a/model-00040-of-00041.safetensors b/model-00040-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53406dd1a4ec4e2d823cceb540464558c6016b06 --- /dev/null +++ b/model-00040-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c482478e5d4f5e0e4d77ba4cb4f0ba75a749c94e526dee1ef6c1e5281ebcf22 +size 5360945920 diff --git a/model-00041-of-00041.safetensors b/model-00041-of-00041.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f3bc6616b92119772afa46e54b9d3fe288fb810 --- /dev/null +++ b/model-00041-of-00041.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea489fae1616921703724208cf7c6b9aa2ef4eae0e0acc06f1e456f5cdd8646 +size 1023744840 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..67dfe8031a72c87ec5d3ffecf7f4fb1579423330 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,18113 @@ +{ + "metadata": { + "total_size": 107710933120 + }, + "weight_map": { + "model.language_model.embed_tokens.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.64.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.64.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.65.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.65.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.66.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.66.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.67.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.67.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.68.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.68.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.69.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.69.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.70.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.70.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.71.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.71.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.72.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.72.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.73.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.73.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.74.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.74.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.75.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.75.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.76.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.76.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.77.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.77.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.78.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.78.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.79.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.79.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.80.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.80.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.81.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.81.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.82.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.82.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.83.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.83.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.84.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.84.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.85.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.85.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.86.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.86.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.87.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.87.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.88.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.88.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.89.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.89.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.90.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.90.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.91.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.91.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.92.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.92.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.93.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.93.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.94.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.94.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.95.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.95.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.96.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.96.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.97.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.97.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.98.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.98.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.99.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.99.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.100.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.100.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.101.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.101.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.102.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.102.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.103.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.103.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.104.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.104.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.105.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.105.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.106.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.106.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.107.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.107.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.108.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.108.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.109.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.109.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.110.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.110.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.111.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.111.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.112.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.112.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.113.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.113.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.114.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.114.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.115.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.115.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.116.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.116.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.117.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.117.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.118.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.118.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.119.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.119.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.120.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.120.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.121.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.121.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.122.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.122.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.123.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.123.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.124.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.124.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.125.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.125.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.126.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.126.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.127.gate_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.127.up_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.64.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.65.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.66.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.67.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.68.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.69.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.70.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.71.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.72.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.73.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.74.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.75.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.76.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.77.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.78.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.79.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.80.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.81.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.82.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.83.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.84.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.85.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.86.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.87.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.88.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.89.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.90.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.91.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.92.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.93.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.94.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.95.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.96.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.97.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.98.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.99.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.100.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.101.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.102.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.103.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.104.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.105.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.106.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.107.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.108.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.109.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.110.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.111.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.112.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.113.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.114.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.115.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.116.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.117.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.118.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.119.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.120.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.121.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.122.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.123.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.124.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.125.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.126.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.experts.127.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.gate.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.q_proj.bias": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.k_proj.bias": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.self_attn.v_proj.bias": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.0.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.1.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.4.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.4.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.5.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.5.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.6.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.6.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.7.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.7.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.8.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.8.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.9.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.9.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.10.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.10.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.11.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.11.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.12.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.12.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.13.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.13.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.14.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.14.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.15.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.15.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.16.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.16.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.17.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.17.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.18.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.18.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.19.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.19.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.20.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.20.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.21.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.21.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.22.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.22.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.23.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.23.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.24.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.24.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.25.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.25.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.26.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.26.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.27.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.27.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.28.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.28.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.29.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.29.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.30.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.30.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.31.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.31.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.32.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.32.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.33.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.33.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.34.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.34.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.35.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.35.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.36.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.36.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.37.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.37.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.38.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.39.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.39.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.40.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.40.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.41.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.41.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.42.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.42.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.43.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.43.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.44.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.44.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.45.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.45.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.46.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.46.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.47.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.47.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.48.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.49.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.51.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.52.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.53.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.54.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.55.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.57.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.58.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.59.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.60.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.61.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.62.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.63.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.64.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.64.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.65.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.65.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.66.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.66.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.67.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.67.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.68.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.68.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.69.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.69.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.70.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.70.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.71.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.71.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.72.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.72.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.73.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.73.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.74.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.74.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.75.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.75.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.76.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.76.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.77.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.77.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.78.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.78.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.79.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.79.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.80.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.80.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.81.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.81.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.82.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.82.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.83.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.83.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.84.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.84.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.85.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.85.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.86.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.86.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.87.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.87.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.88.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.88.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.89.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.89.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.90.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.90.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.91.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.91.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.92.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.92.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.93.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.93.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.94.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.94.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.95.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.95.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.96.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.96.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.97.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.97.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.98.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.98.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.99.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.99.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.100.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.100.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.101.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.101.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.102.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.102.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.103.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.103.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.104.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.104.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.105.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.105.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.106.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.106.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.107.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.107.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.108.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.108.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.109.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.109.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.110.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.110.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.111.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.111.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.112.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.112.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.113.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.113.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.114.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.114.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.115.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.115.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.116.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.116.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.117.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.117.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.118.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.118.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.119.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.119.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.120.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.120.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.121.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.121.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.122.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.122.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.123.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.123.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.124.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.124.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.125.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.125.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.126.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.126.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.127.gate_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.127.up_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.64.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.65.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.66.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.67.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.68.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.69.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.70.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.72.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.73.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.74.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.75.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.76.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.78.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.79.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.80.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.81.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.82.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.83.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.85.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.86.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.87.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.88.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.89.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.90.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.91.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.92.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.93.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.94.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.95.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.96.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.97.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.98.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.99.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.100.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.101.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.102.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.103.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.104.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.105.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.106.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.107.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.108.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.109.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.110.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.111.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.112.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.113.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.114.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.115.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.116.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.117.down_proj.weight": "model-00002-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.118.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.119.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.120.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.121.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.122.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.123.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.124.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.125.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.126.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.experts.127.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.gate.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.q_proj.bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.k_proj.bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.v_proj.bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.0.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.0.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.1.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.2.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.2.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.3.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.3.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.4.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.4.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.5.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.5.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.6.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.6.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.7.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.7.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.8.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.8.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.9.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.9.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.10.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.10.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.11.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.11.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.12.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.12.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.13.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.13.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.14.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.14.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.15.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.15.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.16.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.16.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.17.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.17.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.18.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.18.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.19.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.19.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.20.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.20.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.21.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.21.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.22.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.22.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.23.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.23.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.24.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.24.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.25.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.25.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.26.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.26.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.27.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.27.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.28.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.28.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.29.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.29.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.30.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.30.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.31.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.31.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.32.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.32.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.33.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.33.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.34.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.34.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.35.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.35.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.36.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.36.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.37.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.37.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.38.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.38.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.39.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.39.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.40.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.40.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.41.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.41.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.42.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.42.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.43.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.43.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.44.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.44.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.45.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.45.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.46.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.46.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.47.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.47.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.48.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.48.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.49.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.49.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.50.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.50.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.51.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.51.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.52.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.52.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.53.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.53.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.54.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.54.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.55.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.55.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.56.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.56.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.57.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.57.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.58.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.58.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.59.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.59.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.60.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.60.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.61.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.61.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.62.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.62.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.63.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.63.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.64.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.64.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.65.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.65.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.66.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.66.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.67.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.67.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.68.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.68.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.69.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.69.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.70.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.70.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.71.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.71.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.72.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.72.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.73.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.73.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.74.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.74.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.75.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.75.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.76.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.76.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.77.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.77.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.78.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.78.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.79.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.79.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.80.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.80.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.81.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.81.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.82.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.82.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.83.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.83.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.84.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.84.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.85.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.85.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.86.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.86.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.87.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.87.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.88.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.88.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.89.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.89.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.90.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.90.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.91.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.91.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.92.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.92.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.93.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.93.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.94.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.94.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.95.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.95.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.96.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.96.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.97.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.97.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.98.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.98.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.99.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.99.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.100.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.100.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.101.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.101.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.102.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.102.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.103.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.103.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.104.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.104.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.105.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.105.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.106.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.106.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.107.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.107.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.108.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.108.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.109.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.109.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.110.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.110.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.111.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.111.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.112.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.112.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.113.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.113.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.114.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.114.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.115.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.115.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.116.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.116.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.117.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.117.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.118.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.118.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.119.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.119.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.120.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.120.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.121.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.121.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.122.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.122.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.123.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.123.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.124.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.124.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.125.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.125.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.126.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.126.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.127.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.127.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.4.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.5.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.6.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.7.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.8.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.9.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.16.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.17.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.19.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.20.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.21.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.22.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.23.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.24.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.25.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.26.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.27.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.29.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.30.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.31.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.33.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.34.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.35.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.36.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.37.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.38.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.39.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.40.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.41.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.42.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.43.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.44.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.45.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.46.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.47.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.48.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.50.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.51.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.52.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.53.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.54.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.55.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.56.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.57.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.58.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.59.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.60.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.61.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.62.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.63.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.64.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.65.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.66.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.67.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.68.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.69.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.70.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.71.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.72.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.73.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.74.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.75.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.76.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.77.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.78.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.79.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.80.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.81.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.82.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.83.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.84.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.85.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.86.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.87.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.88.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.89.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.90.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.91.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.92.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.93.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.94.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.95.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.96.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.97.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.98.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.99.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.100.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.101.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.102.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.103.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.104.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.105.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.106.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.107.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.108.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.109.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.110.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.111.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.112.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.113.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.114.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.115.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.116.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.117.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.118.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.119.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.120.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.121.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.122.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.123.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.124.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.125.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.126.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.experts.127.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.gate.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.shared_experts.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.shared_experts.down_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.mlp.gate.e_score_correction_bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.q_proj.bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.k_proj.bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.3.self_attn.v_proj.bias": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.0.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.0.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.1.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.1.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.2.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.2.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.3.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.3.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.4.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.4.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.5.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.5.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.6.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.6.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.7.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.7.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.8.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.8.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.9.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.9.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.10.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.10.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.11.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.11.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.12.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.12.up_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.13.gate_proj.weight": "model-00003-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.13.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.14.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.14.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.15.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.15.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.16.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.16.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.17.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.17.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.18.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.18.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.19.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.19.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.20.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.20.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.21.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.21.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.22.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.22.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.23.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.23.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.24.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.24.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.25.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.25.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.26.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.26.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.27.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.27.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.28.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.28.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.29.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.29.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.30.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.30.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.31.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.31.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.32.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.32.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.33.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.33.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.34.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.34.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.35.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.35.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.36.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.36.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.37.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.37.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.38.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.38.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.39.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.39.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.40.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.40.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.41.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.41.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.42.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.42.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.43.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.43.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.44.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.44.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.45.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.45.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.46.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.46.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.47.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.47.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.48.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.48.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.49.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.49.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.50.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.50.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.51.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.51.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.52.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.52.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.53.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.53.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.54.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.54.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.55.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.55.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.56.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.56.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.57.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.57.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.58.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.58.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.59.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.59.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.60.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.60.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.61.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.61.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.62.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.62.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.63.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.63.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.64.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.64.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.65.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.65.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.66.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.66.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.67.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.67.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.68.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.68.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.69.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.69.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.70.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.70.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.71.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.71.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.72.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.72.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.73.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.73.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.74.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.74.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.75.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.75.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.76.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.76.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.77.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.77.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.78.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.78.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.79.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.79.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.80.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.80.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.81.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.81.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.82.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.82.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.83.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.83.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.84.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.84.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.85.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.85.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.86.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.86.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.87.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.87.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.88.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.88.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.89.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.89.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.90.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.90.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.91.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.91.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.92.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.92.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.93.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.93.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.94.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.94.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.95.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.95.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.96.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.96.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.97.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.97.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.98.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.98.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.99.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.99.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.100.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.100.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.101.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.101.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.102.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.102.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.103.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.103.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.104.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.104.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.105.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.105.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.106.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.106.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.107.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.107.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.108.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.108.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.109.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.109.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.110.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.110.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.111.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.111.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.112.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.112.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.113.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.113.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.114.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.114.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.115.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.115.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.116.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.116.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.117.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.117.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.118.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.118.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.119.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.119.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.120.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.120.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.121.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.121.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.122.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.122.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.123.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.123.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.124.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.124.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.125.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.125.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.126.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.126.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.127.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.127.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.0.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.1.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.2.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.3.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.4.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.5.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.6.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.7.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.8.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.9.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.11.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.12.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.13.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.14.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.15.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.16.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.17.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.18.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.20.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.21.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.22.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.23.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.24.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.25.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.26.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.28.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.29.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.30.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.32.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.33.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.34.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.35.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.36.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.37.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.38.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.39.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.40.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.43.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.44.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.45.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.46.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.47.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.48.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.49.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.50.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.52.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.54.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.55.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.56.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.57.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.58.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.59.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.60.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.61.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.62.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.63.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.64.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.65.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.66.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.67.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.68.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.69.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.70.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.71.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.72.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.73.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.74.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.75.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.76.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.77.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.78.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.79.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.80.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.81.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.82.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.83.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.84.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.85.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.86.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.87.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.88.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.89.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.90.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.91.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.92.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.93.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.94.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.95.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.96.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.97.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.98.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.99.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.100.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.101.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.102.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.103.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.104.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.105.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.106.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.107.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.108.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.109.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.110.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.111.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.112.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.113.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.114.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.115.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.116.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.117.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.118.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.119.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.120.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.121.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.122.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.123.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.124.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.125.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.126.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.experts.127.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.gate.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.shared_experts.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.shared_experts.down_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.mlp.gate.e_score_correction_bias": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.q_proj.bias": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.k_proj.bias": "model-00004-of-00041.safetensors", + "model.language_model.layers.4.self_attn.v_proj.bias": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.0.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.0.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.1.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.1.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.2.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.2.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.3.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.3.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.4.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.4.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.5.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.5.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.6.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.6.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.7.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.7.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.8.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.8.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.9.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.9.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.10.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.10.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.11.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.11.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.12.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.12.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.13.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.13.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.14.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.14.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.15.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.15.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.16.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.16.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.17.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.17.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.18.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.18.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.19.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.19.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.20.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.20.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.21.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.21.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.22.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.22.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.23.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.23.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.24.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.24.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.25.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.25.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.26.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.26.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.27.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.27.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.28.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.28.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.29.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.29.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.30.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.30.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.31.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.31.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.32.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.32.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.33.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.33.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.34.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.34.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.35.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.35.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.36.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.36.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.37.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.37.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.38.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.38.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.39.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.39.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.40.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.40.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.41.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.41.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.42.gate_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.42.up_proj.weight": "model-00004-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.43.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.43.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.44.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.44.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.45.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.45.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.46.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.46.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.47.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.47.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.48.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.48.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.49.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.49.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.50.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.50.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.51.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.51.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.52.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.52.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.53.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.53.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.54.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.54.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.55.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.55.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.56.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.56.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.57.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.57.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.58.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.58.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.59.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.59.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.60.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.60.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.61.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.61.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.62.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.62.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.63.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.63.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.64.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.64.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.65.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.65.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.66.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.66.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.67.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.67.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.68.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.68.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.69.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.69.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.70.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.70.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.71.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.71.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.72.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.72.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.73.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.73.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.74.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.74.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.75.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.75.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.76.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.76.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.77.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.77.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.78.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.78.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.79.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.79.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.80.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.80.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.81.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.81.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.82.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.82.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.83.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.83.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.84.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.84.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.85.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.85.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.86.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.86.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.87.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.87.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.88.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.88.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.89.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.89.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.90.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.90.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.91.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.91.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.92.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.92.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.93.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.93.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.94.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.94.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.95.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.95.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.96.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.96.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.97.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.97.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.98.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.98.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.99.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.99.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.100.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.100.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.101.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.101.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.102.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.102.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.103.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.103.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.104.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.104.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.105.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.105.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.106.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.106.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.107.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.107.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.108.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.108.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.109.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.109.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.110.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.110.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.111.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.111.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.112.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.112.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.113.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.113.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.114.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.114.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.115.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.115.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.116.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.116.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.117.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.117.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.118.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.118.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.119.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.119.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.120.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.120.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.121.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.121.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.122.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.122.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.123.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.123.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.124.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.124.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.125.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.125.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.126.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.126.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.127.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.127.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.0.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.1.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.2.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.3.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.4.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.5.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.6.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.7.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.8.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.9.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.10.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.11.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.12.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.13.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.14.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.15.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.16.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.17.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.18.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.19.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.20.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.21.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.22.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.23.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.24.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.25.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.26.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.27.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.28.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.29.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.30.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.31.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.32.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.33.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.34.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.35.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.36.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.37.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.38.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.39.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.40.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.41.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.42.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.43.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.44.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.45.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.46.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.47.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.48.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.49.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.50.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.51.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.52.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.53.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.54.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.55.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.56.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.57.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.58.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.59.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.60.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.61.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.62.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.63.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.64.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.65.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.66.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.67.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.68.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.69.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.70.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.71.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.72.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.73.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.74.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.75.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.76.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.77.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.78.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.79.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.80.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.81.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.82.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.83.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.84.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.85.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.86.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.87.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.88.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.89.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.90.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.91.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.92.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.93.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.94.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.95.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.96.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.97.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.98.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.99.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.100.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.101.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.102.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.103.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.104.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.105.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.106.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.107.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.108.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.109.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.110.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.111.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.112.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.113.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.114.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.115.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.116.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.117.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.118.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.119.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.120.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.121.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.122.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.123.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.124.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.125.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.126.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.experts.127.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.shared_experts.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.shared_experts.down_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.gate.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.q_proj.bias": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.k_proj.bias": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.self_attn.v_proj.bias": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.5.mlp.gate.e_score_correction_bias": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.0.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.0.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.1.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.1.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.2.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.2.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.3.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.3.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.4.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.4.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.5.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.5.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.6.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.6.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.7.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.7.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.8.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.8.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.9.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.9.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.10.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.10.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.11.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.11.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.12.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.12.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.13.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.13.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.14.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.14.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.15.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.15.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.16.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.16.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.17.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.17.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.18.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.18.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.19.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.19.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.20.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.20.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.21.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.21.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.22.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.22.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.23.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.23.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.24.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.24.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.25.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.25.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.26.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.26.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.27.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.27.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.28.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.28.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.29.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.29.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.30.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.30.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.31.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.31.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.32.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.32.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.33.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.33.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.34.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.34.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.35.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.35.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.36.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.36.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.37.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.37.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.38.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.38.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.39.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.39.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.40.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.40.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.41.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.41.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.42.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.42.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.43.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.43.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.44.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.44.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.45.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.45.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.46.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.46.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.47.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.47.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.48.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.48.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.49.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.49.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.50.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.50.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.51.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.51.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.52.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.52.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.53.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.53.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.54.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.54.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.55.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.55.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.56.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.56.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.57.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.57.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.58.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.58.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.59.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.59.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.60.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.60.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.61.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.61.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.62.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.62.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.63.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.63.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.64.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.64.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.65.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.65.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.66.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.66.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.67.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.67.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.68.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.68.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.69.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.69.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.70.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.70.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.71.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.71.up_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.72.gate_proj.weight": "model-00005-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.72.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.73.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.73.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.74.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.74.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.75.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.75.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.76.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.76.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.77.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.77.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.78.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.78.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.79.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.79.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.80.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.80.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.81.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.81.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.82.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.82.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.83.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.83.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.84.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.84.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.85.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.85.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.86.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.86.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.87.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.87.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.88.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.88.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.89.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.89.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.90.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.90.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.91.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.91.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.92.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.92.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.93.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.93.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.94.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.94.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.95.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.95.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.96.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.96.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.97.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.97.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.98.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.98.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.99.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.99.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.100.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.100.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.101.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.101.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.102.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.102.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.103.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.103.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.104.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.104.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.105.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.105.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.106.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.106.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.107.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.107.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.108.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.108.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.109.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.109.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.110.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.110.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.111.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.111.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.112.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.112.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.113.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.113.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.114.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.114.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.115.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.115.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.116.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.116.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.117.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.117.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.118.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.118.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.119.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.119.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.120.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.120.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.121.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.121.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.122.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.122.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.123.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.123.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.124.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.124.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.125.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.125.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.126.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.126.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.127.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.127.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.0.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.1.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.2.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.3.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.4.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.5.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.6.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.7.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.8.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.9.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.10.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.11.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.12.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.13.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.14.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.15.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.16.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.17.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.18.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.19.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.20.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.21.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.22.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.23.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.24.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.25.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.26.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.27.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.28.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.29.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.30.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.31.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.32.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.33.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.34.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.35.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.36.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.37.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.38.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.39.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.40.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.41.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.42.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.43.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.44.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.45.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.46.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.47.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.48.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.49.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.50.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.51.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.52.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.53.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.54.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.55.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.56.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.57.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.58.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.59.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.60.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.61.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.62.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.63.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.64.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.65.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.66.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.67.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.68.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.69.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.70.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.71.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.72.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.73.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.74.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.75.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.76.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.77.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.78.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.79.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.80.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.81.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.82.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.83.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.84.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.85.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.86.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.87.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.88.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.89.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.90.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.91.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.92.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.93.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.94.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.95.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.96.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.97.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.98.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.99.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.100.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.101.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.102.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.103.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.104.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.105.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.106.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.107.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.108.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.109.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.110.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.111.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.112.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.113.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.114.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.115.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.116.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.117.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.118.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.119.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.120.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.121.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.122.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.123.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.124.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.125.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.126.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.experts.127.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.gate.e_score_correction_bias": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.gate.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.shared_experts.down_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.q_proj.bias": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.k_proj.bias": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.self_attn.v_proj.bias": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.mlp.shared_experts.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.0.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.0.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.1.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.1.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.2.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.2.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.3.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.3.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.4.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.4.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.5.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.5.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.6.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.6.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.7.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.7.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.8.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.8.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.9.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.9.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.10.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.10.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.11.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.11.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.12.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.12.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.13.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.13.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.14.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.14.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.15.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.15.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.16.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.16.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.17.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.17.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.18.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.18.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.19.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.19.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.20.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.20.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.21.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.21.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.22.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.22.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.23.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.23.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.24.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.24.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.25.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.25.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.26.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.26.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.27.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.27.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.28.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.28.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.29.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.29.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.30.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.30.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.31.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.31.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.32.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.32.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.33.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.33.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.34.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.34.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.35.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.35.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.36.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.36.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.37.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.37.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.38.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.38.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.39.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.39.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.40.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.40.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.41.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.41.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.42.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.42.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.43.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.43.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.44.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.44.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.45.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.45.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.46.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.46.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.47.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.47.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.48.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.48.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.49.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.49.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.50.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.50.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.51.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.51.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.52.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.52.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.53.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.53.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.54.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.54.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.55.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.55.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.56.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.56.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.57.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.57.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.58.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.58.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.59.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.59.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.60.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.60.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.61.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.61.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.62.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.62.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.63.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.63.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.64.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.64.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.65.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.65.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.66.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.66.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.67.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.67.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.68.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.68.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.69.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.69.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.70.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.70.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.71.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.71.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.72.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.72.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.73.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.73.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.74.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.74.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.75.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.75.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.76.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.76.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.77.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.77.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.78.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.78.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.79.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.79.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.80.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.80.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.81.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.81.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.82.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.82.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.83.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.83.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.84.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.84.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.85.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.85.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.86.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.86.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.87.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.87.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.88.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.88.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.89.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.89.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.90.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.90.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.91.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.91.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.92.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.92.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.93.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.93.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.94.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.94.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.95.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.95.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.96.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.96.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.97.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.97.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.98.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.98.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.99.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.99.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.100.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.100.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.101.gate_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.101.up_proj.weight": "model-00006-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.102.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.102.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.103.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.103.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.104.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.104.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.105.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.105.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.106.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.106.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.107.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.107.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.108.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.108.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.109.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.109.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.110.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.110.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.111.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.111.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.112.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.112.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.113.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.113.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.114.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.114.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.115.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.115.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.116.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.116.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.117.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.117.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.118.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.118.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.119.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.119.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.120.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.120.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.121.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.121.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.122.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.122.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.123.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.123.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.124.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.124.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.125.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.125.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.126.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.126.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.127.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.127.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.0.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.1.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.2.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.3.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.4.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.5.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.6.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.7.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.8.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.9.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.10.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.11.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.12.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.13.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.14.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.15.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.16.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.17.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.18.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.19.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.20.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.21.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.22.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.23.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.24.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.25.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.26.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.27.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.28.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.29.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.30.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.31.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.32.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.33.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.34.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.35.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.36.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.37.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.38.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.39.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.40.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.41.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.42.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.43.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.44.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.45.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.46.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.47.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.48.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.49.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.50.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.51.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.52.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.53.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.54.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.55.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.56.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.57.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.58.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.59.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.60.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.61.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.62.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.63.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.64.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.65.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.66.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.67.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.68.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.69.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.70.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.71.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.72.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.73.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.74.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.75.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.76.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.77.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.78.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.79.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.80.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.81.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.82.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.83.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.84.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.85.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.86.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.87.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.88.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.89.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.90.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.91.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.92.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.93.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.94.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.95.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.96.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.97.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.98.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.99.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.100.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.101.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.102.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.103.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.104.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.105.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.106.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.107.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.108.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.109.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.110.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.111.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.112.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.113.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.114.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.115.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.116.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.117.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.118.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.119.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.120.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.121.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.122.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.123.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.124.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.125.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.126.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.experts.127.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.gate.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.shared_experts.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.shared_experts.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.mlp.gate.e_score_correction_bias": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.q_proj.bias": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.k_proj.bias": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.self_attn.v_proj.bias": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.0.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.0.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.1.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.1.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.2.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.2.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.3.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.3.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.4.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.4.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.5.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.5.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.6.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.6.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.7.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.7.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.8.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.8.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.9.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.9.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.10.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.10.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.11.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.11.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.12.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.12.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.13.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.13.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.14.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.14.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.15.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.15.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.16.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.16.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.17.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.17.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.18.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.18.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.19.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.19.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.20.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.20.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.21.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.21.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.22.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.22.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.23.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.23.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.24.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.24.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.25.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.25.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.26.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.26.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.27.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.27.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.28.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.28.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.29.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.29.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.30.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.30.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.31.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.31.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.32.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.32.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.33.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.33.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.34.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.34.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.35.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.35.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.36.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.36.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.37.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.37.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.38.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.38.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.39.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.39.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.40.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.40.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.41.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.41.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.42.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.42.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.43.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.43.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.44.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.44.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.45.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.45.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.46.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.46.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.47.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.47.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.48.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.48.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.49.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.49.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.50.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.50.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.51.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.51.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.52.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.52.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.53.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.53.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.54.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.54.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.55.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.55.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.56.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.56.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.57.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.57.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.58.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.58.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.59.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.59.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.60.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.60.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.61.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.61.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.62.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.62.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.63.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.63.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.64.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.64.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.65.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.65.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.66.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.66.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.67.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.67.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.68.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.68.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.69.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.69.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.70.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.70.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.71.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.71.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.72.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.72.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.73.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.73.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.74.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.74.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.75.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.75.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.76.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.76.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.77.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.77.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.78.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.78.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.79.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.79.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.80.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.80.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.81.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.81.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.82.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.82.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.83.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.83.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.84.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.84.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.85.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.85.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.86.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.86.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.87.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.87.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.88.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.88.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.89.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.89.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.90.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.90.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.91.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.91.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.92.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.92.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.93.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.93.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.94.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.94.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.95.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.95.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.96.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.96.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.97.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.97.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.98.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.98.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.99.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.99.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.100.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.100.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.101.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.101.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.102.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.102.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.103.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.103.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.104.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.104.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.105.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.105.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.106.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.106.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.107.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.107.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.108.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.108.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.109.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.109.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.110.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.110.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.111.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.111.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.112.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.112.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.113.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.113.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.114.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.114.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.115.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.115.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.116.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.116.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.117.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.117.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.118.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.118.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.119.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.119.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.120.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.120.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.121.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.121.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.122.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.122.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.123.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.123.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.124.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.124.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.125.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.125.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.126.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.126.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.127.gate_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.127.up_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.0.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.1.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.2.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.3.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.4.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.5.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.6.down_proj.weight": "model-00007-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.7.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.8.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.9.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.10.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.11.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.12.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.13.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.14.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.15.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.16.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.17.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.18.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.19.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.20.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.21.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.22.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.23.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.24.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.25.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.26.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.27.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.28.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.29.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.30.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.31.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.32.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.33.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.34.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.35.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.36.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.37.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.38.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.39.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.40.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.41.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.42.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.43.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.44.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.45.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.46.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.47.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.48.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.49.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.50.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.51.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.52.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.53.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.54.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.55.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.56.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.57.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.58.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.59.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.60.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.61.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.62.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.63.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.64.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.65.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.66.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.67.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.68.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.69.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.70.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.71.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.72.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.73.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.74.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.75.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.76.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.77.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.78.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.79.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.80.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.81.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.82.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.83.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.84.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.85.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.86.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.87.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.88.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.89.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.90.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.91.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.92.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.93.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.94.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.95.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.96.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.97.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.98.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.99.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.100.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.101.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.102.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.103.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.104.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.105.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.106.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.107.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.108.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.109.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.110.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.111.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.112.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.113.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.114.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.115.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.116.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.117.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.118.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.119.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.120.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.121.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.122.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.123.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.124.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.125.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.126.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.experts.127.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.gate.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.shared_experts.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.shared_experts.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.mlp.gate.e_score_correction_bias": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.q_proj.bias": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.k_proj.bias": "model-00008-of-00041.safetensors", + "model.language_model.layers.8.self_attn.v_proj.bias": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.0.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.0.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.1.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.1.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.2.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.2.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.3.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.3.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.4.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.4.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.5.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.5.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.6.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.6.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.7.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.7.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.8.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.8.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.9.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.9.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.10.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.10.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.11.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.11.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.12.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.12.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.13.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.13.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.14.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.14.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.15.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.15.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.16.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.16.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.17.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.17.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.18.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.18.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.19.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.19.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.20.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.20.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.21.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.21.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.22.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.22.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.23.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.23.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.24.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.24.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.25.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.25.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.26.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.26.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.27.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.27.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.28.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.28.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.29.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.29.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.30.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.30.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.31.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.31.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.32.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.32.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.33.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.33.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.34.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.34.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.35.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.35.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.36.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.36.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.37.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.37.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.38.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.38.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.39.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.39.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.40.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.40.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.41.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.41.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.42.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.42.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.43.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.43.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.44.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.44.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.45.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.45.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.46.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.46.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.47.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.47.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.48.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.48.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.49.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.49.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.50.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.50.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.51.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.51.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.52.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.52.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.53.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.53.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.54.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.54.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.55.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.55.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.56.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.56.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.57.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.57.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.58.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.58.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.59.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.59.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.60.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.60.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.61.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.61.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.62.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.62.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.63.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.63.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.64.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.64.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.65.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.65.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.66.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.66.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.67.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.67.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.68.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.68.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.69.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.69.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.70.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.70.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.71.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.71.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.72.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.72.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.73.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.73.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.74.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.74.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.75.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.75.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.76.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.76.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.77.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.77.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.78.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.78.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.79.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.79.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.80.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.80.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.81.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.81.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.82.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.82.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.83.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.83.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.84.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.84.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.85.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.85.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.86.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.86.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.87.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.87.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.88.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.88.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.89.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.89.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.90.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.90.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.91.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.91.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.92.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.92.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.93.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.93.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.94.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.94.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.95.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.95.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.96.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.96.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.97.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.97.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.98.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.98.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.99.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.99.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.100.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.100.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.101.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.101.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.102.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.102.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.103.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.103.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.104.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.104.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.105.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.105.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.106.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.106.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.107.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.107.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.108.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.108.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.109.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.109.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.110.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.110.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.111.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.111.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.112.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.112.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.113.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.113.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.114.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.114.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.115.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.115.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.116.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.116.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.117.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.117.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.118.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.118.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.119.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.119.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.120.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.120.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.121.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.121.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.122.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.122.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.123.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.123.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.124.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.124.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.125.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.125.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.126.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.126.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.127.gate_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.127.up_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.0.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.1.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.2.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.3.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.4.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.5.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.6.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.7.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.8.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.9.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.10.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.11.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.12.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.13.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.14.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.15.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.16.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.17.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.18.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.19.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.20.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.21.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.22.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.23.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.24.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.25.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.26.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.27.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.28.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.29.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.30.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.31.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.32.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.33.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.34.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.35.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.36.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.37.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.38.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.39.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.40.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.41.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.42.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.43.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.44.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.45.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.46.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.47.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.48.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.49.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.50.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.51.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.52.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.53.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.54.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.55.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.56.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.57.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.58.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.59.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.60.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.61.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.62.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.63.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.64.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.65.down_proj.weight": "model-00008-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.66.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.67.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.68.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.69.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.70.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.71.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.72.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.73.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.74.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.75.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.76.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.77.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.78.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.79.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.80.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.81.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.82.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.83.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.84.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.85.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.86.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.87.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.88.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.89.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.90.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.91.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.92.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.93.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.94.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.95.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.96.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.97.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.98.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.99.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.100.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.101.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.102.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.103.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.104.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.105.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.106.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.107.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.108.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.109.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.110.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.111.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.112.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.113.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.114.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.115.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.116.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.117.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.118.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.119.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.120.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.121.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.122.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.123.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.124.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.125.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.126.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.experts.127.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.gate.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.shared_experts.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.q_proj.bias": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.k_proj.bias": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.self_attn.v_proj.bias": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.shared_experts.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.9.mlp.gate.e_score_correction_bias": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.0.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.0.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.1.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.1.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.2.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.2.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.3.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.3.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.4.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.4.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.5.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.5.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.6.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.6.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.7.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.7.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.8.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.8.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.9.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.9.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.10.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.10.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.11.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.11.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.12.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.12.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.13.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.13.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.14.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.14.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.15.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.15.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.16.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.16.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.17.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.17.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.18.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.18.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.19.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.19.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.20.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.20.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.21.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.21.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.22.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.22.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.23.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.23.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.24.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.24.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.25.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.25.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.26.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.26.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.27.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.27.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.28.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.28.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.29.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.29.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.30.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.30.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.31.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.31.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.32.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.32.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.33.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.33.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.34.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.34.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.35.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.35.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.36.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.36.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.37.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.37.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.38.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.38.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.39.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.39.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.40.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.40.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.41.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.41.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.42.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.42.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.43.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.43.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.44.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.44.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.45.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.45.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.46.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.46.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.47.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.47.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.48.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.48.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.49.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.49.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.50.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.50.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.51.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.51.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.52.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.52.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.53.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.53.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.54.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.54.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.55.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.55.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.56.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.56.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.57.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.57.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.58.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.58.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.59.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.59.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.60.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.60.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.61.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.61.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.62.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.62.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.63.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.63.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.64.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.64.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.65.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.65.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.66.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.66.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.67.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.67.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.68.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.68.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.69.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.69.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.70.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.70.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.71.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.71.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.72.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.72.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.73.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.73.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.74.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.74.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.75.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.75.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.76.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.76.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.77.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.77.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.78.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.78.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.79.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.79.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.80.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.80.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.81.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.81.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.82.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.82.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.83.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.83.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.84.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.84.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.85.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.85.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.86.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.86.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.87.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.87.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.88.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.88.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.89.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.89.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.90.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.90.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.91.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.91.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.92.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.92.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.93.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.93.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.94.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.94.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.95.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.95.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.96.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.96.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.97.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.97.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.98.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.98.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.99.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.99.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.100.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.100.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.101.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.101.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.102.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.102.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.103.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.103.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.104.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.104.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.105.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.105.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.106.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.106.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.107.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.107.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.108.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.108.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.109.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.109.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.110.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.110.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.111.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.111.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.112.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.112.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.113.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.113.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.114.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.114.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.115.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.115.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.116.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.116.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.117.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.117.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.118.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.118.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.119.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.119.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.120.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.120.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.121.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.121.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.122.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.122.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.123.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.123.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.124.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.124.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.125.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.125.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.126.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.126.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.127.gate_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.127.up_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.0.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.1.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.2.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.3.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.4.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.5.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.6.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.7.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.8.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.9.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.10.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.11.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.12.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.13.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.14.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.15.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.16.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.17.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.18.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.19.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.20.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.21.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.22.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.23.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.24.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.25.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.26.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.27.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.28.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.29.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.30.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.31.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.32.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.33.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.34.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.35.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.36.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.37.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.38.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.39.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.40.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.41.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.42.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.43.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.44.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.45.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.46.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.47.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.48.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.49.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.50.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.51.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.52.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.53.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.54.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.55.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.56.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.57.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.58.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.59.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.60.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.61.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.62.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.63.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.64.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.65.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.66.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.67.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.68.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.69.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.70.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.71.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.72.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.73.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.74.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.75.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.76.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.77.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.78.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.79.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.80.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.81.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.82.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.83.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.84.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.85.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.86.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.87.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.88.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.89.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.90.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.91.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.92.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.93.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.94.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.95.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.96.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.97.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.98.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.99.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.100.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.101.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.102.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.103.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.104.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.105.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.106.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.107.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.108.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.109.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.110.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.111.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.112.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.113.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.114.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.115.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.116.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.117.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.118.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.119.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.120.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.121.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.122.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.123.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.124.down_proj.weight": "model-00009-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.125.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.126.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.experts.127.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.shared_experts.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.shared_experts.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.gate.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.q_proj.bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.k_proj.bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.self_attn.v_proj.bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.10.mlp.gate.e_score_correction_bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.0.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.0.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.1.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.1.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.2.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.2.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.3.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.3.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.4.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.4.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.5.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.5.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.6.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.6.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.7.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.7.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.8.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.8.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.9.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.9.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.10.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.10.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.11.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.11.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.12.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.12.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.13.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.13.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.14.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.14.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.15.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.15.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.16.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.16.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.17.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.17.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.18.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.18.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.19.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.19.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.20.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.20.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.21.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.21.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.22.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.22.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.23.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.23.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.24.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.24.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.25.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.25.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.26.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.26.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.27.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.27.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.28.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.28.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.29.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.29.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.30.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.30.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.31.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.31.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.32.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.32.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.33.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.33.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.34.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.34.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.35.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.35.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.36.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.36.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.37.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.37.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.38.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.38.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.39.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.39.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.40.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.40.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.41.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.41.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.42.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.42.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.43.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.43.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.44.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.44.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.45.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.45.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.46.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.46.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.47.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.47.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.48.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.48.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.49.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.49.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.50.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.50.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.51.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.51.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.52.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.52.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.53.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.53.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.54.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.54.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.55.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.55.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.56.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.56.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.57.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.57.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.58.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.58.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.59.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.59.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.60.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.60.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.61.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.61.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.62.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.62.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.63.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.63.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.64.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.64.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.65.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.65.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.66.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.66.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.67.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.67.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.68.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.68.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.69.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.69.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.70.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.70.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.71.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.71.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.72.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.72.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.73.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.73.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.74.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.74.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.75.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.75.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.76.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.76.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.77.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.77.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.78.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.78.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.79.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.79.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.80.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.80.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.81.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.81.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.82.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.82.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.83.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.83.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.84.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.84.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.85.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.85.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.86.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.86.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.87.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.87.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.88.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.88.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.89.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.89.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.90.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.90.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.91.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.91.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.92.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.92.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.93.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.93.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.94.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.94.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.95.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.95.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.96.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.96.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.97.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.97.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.98.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.98.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.99.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.99.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.100.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.100.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.101.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.101.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.102.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.102.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.103.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.103.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.104.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.104.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.105.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.105.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.106.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.106.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.107.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.107.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.108.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.108.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.109.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.109.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.110.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.110.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.111.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.111.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.112.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.112.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.113.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.113.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.114.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.114.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.115.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.115.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.116.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.116.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.117.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.117.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.118.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.118.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.119.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.119.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.120.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.120.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.121.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.121.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.122.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.122.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.123.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.123.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.124.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.124.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.125.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.125.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.126.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.126.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.127.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.127.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.0.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.1.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.2.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.3.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.4.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.5.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.6.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.7.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.8.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.9.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.10.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.11.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.12.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.13.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.14.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.15.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.16.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.17.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.18.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.19.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.20.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.21.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.22.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.23.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.24.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.25.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.26.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.27.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.28.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.29.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.30.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.31.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.32.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.33.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.34.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.35.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.36.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.37.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.38.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.39.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.40.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.41.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.42.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.43.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.44.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.45.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.46.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.47.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.48.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.49.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.50.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.51.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.52.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.53.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.54.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.55.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.56.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.57.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.58.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.59.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.60.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.61.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.62.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.63.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.64.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.65.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.66.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.67.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.68.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.69.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.70.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.71.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.72.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.73.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.74.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.75.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.76.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.77.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.78.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.79.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.80.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.81.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.82.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.83.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.84.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.85.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.86.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.87.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.88.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.89.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.90.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.91.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.92.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.93.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.94.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.95.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.96.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.97.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.98.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.99.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.100.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.101.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.102.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.103.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.104.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.105.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.106.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.107.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.108.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.109.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.110.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.111.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.112.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.113.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.114.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.115.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.116.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.117.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.118.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.119.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.120.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.121.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.122.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.123.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.124.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.125.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.126.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.experts.127.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.gate.e_score_correction_bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.shared_experts.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.gate.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.mlp.shared_experts.down_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.q_proj.bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.k_proj.bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.self_attn.v_proj.bias": "model-00010-of-00041.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.0.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.0.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.1.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.1.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.2.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.2.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.3.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.3.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.4.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.4.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.5.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.5.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.6.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.6.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.7.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.7.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.8.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.8.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.9.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.9.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.10.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.10.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.11.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.11.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.12.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.12.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.13.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.13.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.14.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.14.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.15.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.15.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.16.gate_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.16.up_proj.weight": "model-00010-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.17.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.17.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.18.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.18.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.19.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.19.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.20.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.20.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.21.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.21.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.22.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.22.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.23.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.23.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.24.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.24.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.25.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.25.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.26.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.26.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.27.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.27.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.28.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.28.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.29.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.29.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.30.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.30.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.31.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.31.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.32.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.32.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.33.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.33.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.34.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.34.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.35.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.35.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.36.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.36.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.37.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.37.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.38.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.38.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.39.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.39.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.40.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.40.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.41.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.41.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.42.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.42.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.43.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.43.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.44.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.44.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.45.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.45.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.46.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.46.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.47.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.47.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.48.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.48.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.49.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.49.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.50.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.50.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.51.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.51.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.52.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.52.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.53.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.53.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.54.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.54.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.55.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.55.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.56.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.56.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.57.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.57.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.58.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.58.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.59.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.59.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.60.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.60.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.61.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.61.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.62.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.62.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.63.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.63.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.64.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.64.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.65.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.65.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.66.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.66.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.67.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.67.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.68.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.68.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.69.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.69.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.70.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.70.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.71.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.71.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.72.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.72.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.73.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.73.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.74.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.74.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.75.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.75.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.76.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.76.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.77.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.77.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.78.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.78.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.79.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.79.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.80.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.80.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.81.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.81.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.82.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.82.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.83.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.83.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.84.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.84.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.85.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.85.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.86.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.86.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.87.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.87.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.88.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.88.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.89.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.89.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.90.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.90.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.91.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.91.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.92.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.92.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.93.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.93.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.94.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.94.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.95.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.95.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.96.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.96.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.97.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.97.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.98.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.98.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.99.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.99.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.100.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.100.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.101.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.101.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.102.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.102.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.103.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.103.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.104.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.104.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.105.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.105.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.106.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.106.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.107.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.107.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.108.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.108.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.109.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.109.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.110.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.110.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.111.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.111.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.112.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.112.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.113.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.113.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.114.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.114.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.115.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.115.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.116.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.116.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.117.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.117.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.118.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.118.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.119.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.119.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.120.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.120.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.121.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.121.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.122.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.122.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.123.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.123.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.124.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.124.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.125.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.125.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.126.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.126.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.127.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.127.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.0.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.1.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.2.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.3.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.4.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.5.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.6.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.7.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.8.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.9.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.10.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.11.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.12.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.13.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.14.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.15.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.16.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.17.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.18.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.19.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.20.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.21.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.22.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.23.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.24.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.25.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.26.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.27.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.28.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.29.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.30.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.31.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.32.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.33.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.34.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.35.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.36.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.37.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.38.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.39.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.40.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.41.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.42.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.43.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.44.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.45.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.46.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.47.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.48.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.49.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.50.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.51.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.52.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.53.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.54.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.55.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.56.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.57.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.58.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.59.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.60.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.61.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.62.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.63.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.64.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.65.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.66.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.67.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.68.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.69.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.70.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.71.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.72.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.73.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.74.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.75.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.76.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.77.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.78.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.79.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.80.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.81.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.82.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.83.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.84.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.85.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.86.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.87.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.88.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.89.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.90.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.91.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.92.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.93.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.94.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.95.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.96.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.97.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.98.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.99.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.100.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.101.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.102.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.103.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.104.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.105.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.106.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.107.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.108.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.109.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.110.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.111.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.112.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.113.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.114.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.115.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.116.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.117.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.118.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.119.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.120.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.121.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.122.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.123.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.124.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.125.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.126.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.experts.127.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.gate.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.shared_experts.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.shared_experts.down_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.mlp.gate.e_score_correction_bias": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.q_proj.bias": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.k_proj.bias": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.self_attn.v_proj.bias": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.0.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.0.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.1.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.1.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.2.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.2.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.3.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.3.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.4.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.4.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.5.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.5.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.6.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.6.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.7.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.7.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.8.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.8.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.9.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.9.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.10.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.10.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.11.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.11.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.12.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.12.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.13.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.13.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.14.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.14.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.15.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.15.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.16.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.16.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.17.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.17.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.18.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.18.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.19.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.19.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.20.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.20.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.21.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.21.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.22.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.22.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.23.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.23.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.24.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.24.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.25.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.25.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.26.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.26.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.27.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.27.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.28.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.28.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.29.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.29.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.30.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.30.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.31.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.31.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.32.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.32.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.33.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.33.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.34.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.34.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.35.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.35.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.36.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.36.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.37.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.37.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.38.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.38.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.39.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.39.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.40.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.40.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.41.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.41.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.42.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.42.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.43.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.43.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.44.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.44.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.45.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.45.up_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.46.gate_proj.weight": "model-00011-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.46.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.47.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.47.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.48.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.48.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.49.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.49.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.50.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.50.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.51.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.51.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.52.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.52.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.53.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.53.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.54.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.54.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.55.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.55.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.56.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.56.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.57.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.57.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.58.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.58.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.59.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.59.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.60.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.60.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.61.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.61.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.62.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.62.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.63.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.63.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.64.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.64.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.65.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.65.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.66.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.66.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.67.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.67.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.68.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.68.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.69.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.69.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.70.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.70.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.71.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.71.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.72.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.72.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.73.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.73.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.74.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.74.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.75.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.75.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.76.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.76.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.77.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.77.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.78.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.78.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.79.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.79.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.80.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.80.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.81.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.81.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.82.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.82.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.83.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.83.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.84.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.84.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.85.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.85.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.86.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.86.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.87.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.87.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.88.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.88.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.89.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.89.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.90.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.90.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.91.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.91.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.92.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.92.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.93.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.93.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.94.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.94.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.95.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.95.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.96.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.96.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.97.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.97.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.98.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.98.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.99.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.99.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.100.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.100.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.101.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.101.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.102.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.102.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.103.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.103.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.104.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.104.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.105.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.105.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.106.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.106.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.107.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.107.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.108.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.108.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.109.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.109.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.110.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.110.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.111.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.111.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.112.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.112.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.113.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.113.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.114.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.114.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.115.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.115.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.116.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.116.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.117.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.117.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.118.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.118.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.119.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.119.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.120.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.120.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.121.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.121.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.122.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.122.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.123.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.123.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.124.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.124.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.125.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.125.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.126.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.126.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.127.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.127.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.0.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.1.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.2.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.3.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.4.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.5.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.6.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.7.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.8.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.9.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.10.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.11.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.12.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.13.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.14.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.15.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.16.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.17.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.18.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.19.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.20.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.21.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.22.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.23.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.24.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.25.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.26.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.27.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.28.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.29.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.30.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.31.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.32.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.33.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.34.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.35.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.36.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.37.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.38.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.39.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.40.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.41.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.42.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.43.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.44.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.45.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.46.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.47.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.48.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.49.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.50.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.51.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.52.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.53.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.54.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.55.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.56.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.57.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.58.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.59.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.60.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.61.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.62.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.63.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.64.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.65.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.66.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.67.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.68.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.69.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.70.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.71.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.72.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.73.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.74.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.75.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.76.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.77.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.78.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.79.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.80.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.81.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.82.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.83.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.84.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.85.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.86.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.87.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.88.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.89.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.90.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.91.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.92.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.93.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.94.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.95.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.96.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.97.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.98.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.99.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.100.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.101.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.102.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.103.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.104.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.105.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.106.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.107.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.108.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.109.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.110.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.111.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.112.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.113.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.114.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.115.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.116.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.117.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.118.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.119.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.120.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.121.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.122.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.123.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.124.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.125.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.126.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.experts.127.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.gate.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.shared_experts.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.shared_experts.down_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.q_proj.bias": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.k_proj.bias": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.self_attn.v_proj.bias": "model-00012-of-00041.safetensors", + "model.language_model.layers.13.mlp.gate.e_score_correction_bias": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.0.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.0.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.1.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.1.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.2.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.2.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.3.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.3.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.4.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.4.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.5.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.5.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.6.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.6.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.7.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.7.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.8.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.8.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.9.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.9.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.10.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.10.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.11.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.11.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.12.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.12.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.13.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.13.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.14.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.14.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.15.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.15.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.16.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.16.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.17.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.17.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.18.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.18.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.19.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.19.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.20.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.20.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.21.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.21.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.22.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.22.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.23.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.23.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.24.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.24.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.25.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.25.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.26.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.26.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.27.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.27.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.28.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.28.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.29.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.29.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.30.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.30.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.31.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.31.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.32.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.32.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.33.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.33.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.34.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.34.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.35.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.35.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.36.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.36.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.37.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.37.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.38.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.38.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.39.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.39.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.40.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.40.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.41.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.41.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.42.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.42.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.43.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.43.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.44.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.44.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.45.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.45.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.46.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.46.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.47.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.47.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.48.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.48.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.49.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.49.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.50.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.50.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.51.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.51.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.52.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.52.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.53.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.53.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.54.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.54.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.55.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.55.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.56.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.56.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.57.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.57.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.58.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.58.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.59.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.59.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.60.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.60.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.61.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.61.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.62.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.62.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.63.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.63.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.64.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.64.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.65.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.65.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.66.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.66.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.67.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.67.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.68.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.68.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.69.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.69.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.70.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.70.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.71.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.71.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.72.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.72.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.73.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.73.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.74.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.74.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.75.gate_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.75.up_proj.weight": "model-00012-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.76.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.76.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.77.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.77.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.78.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.78.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.79.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.79.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.80.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.80.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.81.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.81.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.82.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.82.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.83.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.83.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.84.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.84.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.85.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.85.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.86.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.86.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.87.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.87.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.88.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.88.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.89.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.89.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.90.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.90.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.91.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.91.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.92.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.92.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.93.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.93.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.94.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.94.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.95.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.95.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.96.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.96.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.97.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.97.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.98.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.98.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.99.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.99.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.100.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.100.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.101.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.101.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.102.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.102.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.103.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.103.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.104.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.104.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.105.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.105.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.106.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.106.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.107.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.107.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.108.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.108.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.109.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.109.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.110.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.110.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.111.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.111.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.112.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.112.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.113.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.113.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.114.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.114.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.115.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.115.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.116.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.116.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.117.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.117.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.118.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.118.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.119.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.119.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.120.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.120.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.121.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.121.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.122.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.122.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.123.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.123.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.124.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.124.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.125.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.125.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.126.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.126.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.127.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.127.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.0.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.1.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.2.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.3.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.4.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.5.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.6.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.7.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.8.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.9.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.10.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.11.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.12.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.13.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.14.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.15.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.16.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.17.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.18.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.19.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.20.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.21.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.22.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.23.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.24.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.25.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.26.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.27.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.28.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.29.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.30.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.31.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.32.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.33.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.34.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.35.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.36.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.37.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.38.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.39.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.40.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.41.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.42.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.43.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.44.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.45.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.46.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.47.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.48.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.49.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.50.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.51.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.52.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.53.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.54.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.55.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.56.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.57.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.58.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.59.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.60.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.61.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.62.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.63.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.64.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.65.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.66.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.67.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.68.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.69.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.70.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.71.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.72.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.73.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.74.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.75.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.76.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.77.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.78.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.79.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.80.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.81.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.82.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.83.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.84.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.85.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.86.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.87.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.88.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.89.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.90.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.91.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.92.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.93.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.94.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.95.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.96.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.97.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.98.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.99.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.100.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.101.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.102.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.103.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.104.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.105.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.106.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.107.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.108.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.109.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.110.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.111.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.112.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.113.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.114.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.115.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.116.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.117.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.118.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.119.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.120.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.121.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.122.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.123.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.124.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.125.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.126.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.experts.127.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.gate.e_score_correction_bias": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.gate.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.q_proj.bias": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.k_proj.bias": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.self_attn.v_proj.bias": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.shared_experts.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.mlp.shared_experts.down_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.0.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.0.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.1.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.1.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.2.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.2.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.3.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.3.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.4.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.4.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.5.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.5.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.6.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.6.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.7.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.7.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.8.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.8.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.9.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.9.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.10.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.10.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.11.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.11.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.12.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.12.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.13.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.13.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.14.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.14.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.15.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.15.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.16.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.16.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.17.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.17.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.18.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.18.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.19.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.19.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.20.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.20.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.21.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.21.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.22.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.22.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.23.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.23.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.24.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.24.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.25.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.25.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.26.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.26.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.27.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.27.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.28.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.28.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.29.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.29.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.30.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.30.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.31.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.31.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.32.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.32.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.33.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.33.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.34.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.34.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.35.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.35.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.36.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.36.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.37.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.37.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.38.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.38.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.39.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.39.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.40.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.40.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.41.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.41.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.42.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.42.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.43.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.43.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.44.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.44.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.45.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.45.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.46.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.46.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.47.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.47.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.48.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.48.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.49.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.49.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.50.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.50.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.51.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.51.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.52.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.52.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.53.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.53.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.54.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.54.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.55.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.55.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.56.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.56.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.57.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.57.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.58.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.58.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.59.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.59.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.60.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.60.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.61.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.61.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.62.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.62.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.63.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.63.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.64.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.64.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.65.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.65.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.66.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.66.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.67.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.67.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.68.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.68.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.69.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.69.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.70.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.70.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.71.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.71.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.72.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.72.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.73.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.73.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.74.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.74.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.75.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.75.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.76.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.76.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.77.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.77.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.78.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.78.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.79.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.79.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.80.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.80.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.81.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.81.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.82.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.82.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.83.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.83.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.84.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.84.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.85.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.85.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.86.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.86.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.87.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.87.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.88.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.88.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.89.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.89.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.90.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.90.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.91.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.91.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.92.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.92.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.93.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.93.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.94.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.94.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.95.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.95.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.96.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.96.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.97.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.97.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.98.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.98.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.99.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.99.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.100.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.100.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.101.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.101.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.102.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.102.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.103.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.103.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.104.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.104.up_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.105.gate_proj.weight": "model-00013-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.105.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.106.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.106.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.107.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.107.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.108.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.108.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.109.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.109.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.110.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.110.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.111.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.111.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.112.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.112.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.113.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.113.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.114.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.114.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.115.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.115.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.116.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.116.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.117.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.117.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.118.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.118.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.119.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.119.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.120.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.120.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.121.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.121.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.122.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.122.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.123.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.123.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.124.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.124.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.125.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.125.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.126.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.126.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.127.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.127.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.0.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.1.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.2.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.3.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.4.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.5.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.6.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.7.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.8.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.9.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.10.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.11.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.12.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.13.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.14.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.15.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.16.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.17.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.18.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.19.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.20.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.21.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.22.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.23.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.24.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.25.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.26.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.27.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.28.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.29.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.30.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.31.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.32.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.33.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.34.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.35.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.36.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.37.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.38.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.39.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.40.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.41.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.42.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.43.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.44.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.45.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.46.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.47.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.48.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.49.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.50.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.51.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.52.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.53.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.54.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.55.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.56.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.57.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.58.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.59.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.60.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.61.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.62.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.63.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.64.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.65.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.66.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.67.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.68.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.69.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.70.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.71.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.72.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.73.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.74.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.75.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.76.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.77.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.78.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.79.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.80.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.81.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.82.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.83.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.84.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.85.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.86.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.87.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.88.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.89.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.90.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.91.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.92.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.93.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.94.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.95.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.96.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.97.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.98.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.99.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.100.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.101.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.102.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.103.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.104.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.105.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.106.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.107.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.108.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.109.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.110.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.111.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.112.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.113.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.114.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.115.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.116.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.117.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.118.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.119.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.120.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.121.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.122.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.123.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.124.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.125.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.126.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.experts.127.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.shared_experts.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.shared_experts.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.gate.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.mlp.gate.e_score_correction_bias": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.q_proj.bias": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.k_proj.bias": "model-00014-of-00041.safetensors", + "model.language_model.layers.15.self_attn.v_proj.bias": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.0.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.0.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.1.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.1.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.2.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.2.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.3.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.3.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.4.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.4.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.5.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.5.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.6.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.6.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.7.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.7.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.8.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.8.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.9.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.9.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.10.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.10.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.11.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.11.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.12.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.12.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.13.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.13.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.14.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.14.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.15.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.15.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.16.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.16.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.17.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.17.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.18.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.18.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.19.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.19.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.20.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.20.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.21.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.21.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.22.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.22.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.23.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.23.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.24.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.24.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.25.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.25.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.26.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.26.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.27.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.27.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.28.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.28.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.29.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.29.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.30.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.30.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.31.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.31.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.32.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.32.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.33.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.33.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.34.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.34.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.35.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.35.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.36.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.36.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.37.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.37.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.38.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.38.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.39.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.39.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.40.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.40.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.41.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.41.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.42.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.42.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.43.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.43.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.44.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.44.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.45.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.45.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.46.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.46.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.47.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.47.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.48.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.48.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.49.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.49.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.50.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.50.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.51.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.51.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.52.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.52.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.53.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.53.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.54.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.54.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.55.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.55.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.56.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.56.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.57.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.57.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.58.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.58.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.59.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.59.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.60.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.60.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.61.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.61.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.62.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.62.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.63.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.63.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.64.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.64.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.65.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.65.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.66.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.66.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.67.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.67.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.68.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.68.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.69.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.69.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.70.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.70.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.71.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.71.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.72.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.72.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.73.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.73.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.74.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.74.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.75.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.75.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.76.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.76.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.77.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.77.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.78.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.78.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.79.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.79.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.80.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.80.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.81.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.81.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.82.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.82.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.83.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.83.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.84.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.84.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.85.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.85.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.86.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.86.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.87.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.87.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.88.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.88.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.89.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.89.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.90.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.90.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.91.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.91.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.92.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.92.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.93.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.93.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.94.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.94.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.95.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.95.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.96.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.96.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.97.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.97.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.98.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.98.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.99.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.99.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.100.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.100.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.101.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.101.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.102.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.102.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.103.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.103.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.104.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.104.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.105.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.105.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.106.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.106.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.107.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.107.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.108.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.108.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.109.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.109.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.110.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.110.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.111.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.111.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.112.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.112.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.113.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.113.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.114.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.114.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.115.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.115.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.116.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.116.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.117.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.117.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.118.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.118.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.119.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.119.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.120.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.120.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.121.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.121.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.122.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.122.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.123.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.123.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.124.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.124.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.125.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.125.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.126.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.126.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.127.gate_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.127.up_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.0.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.1.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.2.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.3.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.4.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.5.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.6.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.7.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.8.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.9.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.10.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.11.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.12.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.13.down_proj.weight": "model-00014-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.14.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.15.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.16.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.17.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.18.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.19.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.20.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.21.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.22.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.23.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.24.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.25.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.26.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.27.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.28.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.29.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.30.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.31.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.32.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.33.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.34.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.35.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.36.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.37.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.38.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.39.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.40.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.41.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.42.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.43.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.44.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.45.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.46.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.47.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.48.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.49.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.50.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.51.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.52.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.53.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.54.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.55.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.56.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.57.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.58.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.59.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.60.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.61.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.62.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.63.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.64.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.65.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.66.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.67.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.68.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.69.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.70.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.71.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.72.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.73.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.74.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.75.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.76.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.77.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.78.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.79.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.80.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.81.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.82.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.83.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.84.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.85.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.86.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.87.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.88.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.89.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.90.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.91.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.92.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.93.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.94.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.95.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.96.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.97.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.98.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.99.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.100.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.101.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.102.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.103.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.104.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.105.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.106.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.107.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.108.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.109.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.110.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.111.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.112.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.113.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.114.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.115.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.116.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.117.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.118.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.119.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.120.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.121.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.122.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.123.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.124.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.125.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.126.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.experts.127.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.shared_experts.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.shared_experts.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.gate.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.q_proj.bias": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.k_proj.bias": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.self_attn.v_proj.bias": "model-00015-of-00041.safetensors", + "model.language_model.layers.16.mlp.gate.e_score_correction_bias": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.0.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.0.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.1.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.1.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.2.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.2.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.3.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.3.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.4.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.4.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.5.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.5.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.6.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.6.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.7.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.7.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.8.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.8.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.9.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.9.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.10.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.10.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.11.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.11.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.12.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.12.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.13.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.13.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.14.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.14.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.15.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.15.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.16.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.16.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.17.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.17.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.18.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.18.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.19.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.19.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.20.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.20.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.21.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.21.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.22.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.22.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.23.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.23.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.24.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.24.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.25.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.25.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.26.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.26.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.27.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.27.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.28.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.28.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.29.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.29.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.30.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.30.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.31.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.31.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.32.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.32.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.33.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.33.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.34.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.34.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.35.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.35.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.36.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.36.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.37.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.37.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.38.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.38.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.39.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.39.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.40.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.40.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.41.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.41.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.42.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.42.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.43.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.43.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.44.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.44.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.45.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.45.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.46.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.46.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.47.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.47.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.48.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.48.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.49.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.49.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.50.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.50.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.51.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.51.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.52.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.52.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.53.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.53.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.54.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.54.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.55.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.55.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.56.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.56.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.57.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.57.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.58.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.58.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.59.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.59.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.60.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.60.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.61.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.61.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.62.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.62.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.63.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.63.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.64.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.64.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.65.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.65.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.66.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.66.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.67.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.67.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.68.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.68.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.69.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.69.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.70.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.70.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.71.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.71.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.72.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.72.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.73.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.73.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.74.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.74.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.75.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.75.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.76.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.76.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.77.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.77.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.78.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.78.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.79.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.79.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.80.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.80.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.81.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.81.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.82.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.82.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.83.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.83.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.84.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.84.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.85.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.85.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.86.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.86.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.87.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.87.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.88.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.88.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.89.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.89.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.90.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.90.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.91.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.91.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.92.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.92.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.93.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.93.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.94.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.94.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.95.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.95.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.96.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.96.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.97.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.97.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.98.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.98.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.99.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.99.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.100.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.100.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.101.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.101.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.102.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.102.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.103.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.103.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.104.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.104.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.105.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.105.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.106.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.106.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.107.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.107.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.108.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.108.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.109.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.109.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.110.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.110.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.111.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.111.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.112.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.112.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.113.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.113.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.114.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.114.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.115.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.115.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.116.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.116.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.117.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.117.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.118.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.118.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.119.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.119.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.120.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.120.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.121.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.121.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.122.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.122.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.123.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.123.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.124.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.124.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.125.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.125.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.126.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.126.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.127.gate_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.127.up_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.0.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.1.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.2.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.3.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.4.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.5.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.6.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.7.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.8.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.9.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.10.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.11.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.12.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.13.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.14.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.15.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.16.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.17.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.18.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.19.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.20.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.21.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.22.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.23.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.24.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.25.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.26.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.27.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.28.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.29.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.30.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.31.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.32.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.33.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.34.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.35.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.36.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.37.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.38.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.39.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.40.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.41.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.42.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.43.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.44.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.45.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.46.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.47.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.48.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.49.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.50.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.51.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.52.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.53.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.54.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.55.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.56.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.57.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.58.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.59.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.60.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.61.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.62.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.63.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.64.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.65.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.66.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.67.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.68.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.69.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.70.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.71.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.72.down_proj.weight": "model-00015-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.73.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.74.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.75.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.76.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.77.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.78.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.79.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.80.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.81.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.82.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.83.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.84.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.85.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.86.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.87.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.88.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.89.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.90.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.91.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.92.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.93.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.94.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.95.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.96.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.97.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.98.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.99.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.100.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.101.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.102.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.103.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.104.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.105.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.106.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.107.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.108.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.109.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.110.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.111.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.112.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.113.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.114.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.115.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.116.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.117.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.118.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.119.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.120.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.121.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.122.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.123.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.124.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.125.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.126.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.experts.127.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.gate.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.gate.e_score_correction_bias": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.shared_experts.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.mlp.shared_experts.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.q_proj.bias": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.k_proj.bias": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.v_proj.bias": "model-00016-of-00041.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.0.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.0.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.1.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.1.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.2.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.2.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.3.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.3.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.4.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.4.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.5.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.5.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.6.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.6.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.7.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.7.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.8.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.8.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.9.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.9.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.10.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.10.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.11.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.11.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.12.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.12.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.13.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.13.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.14.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.14.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.15.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.15.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.16.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.16.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.17.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.17.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.18.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.18.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.19.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.19.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.20.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.20.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.21.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.21.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.22.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.22.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.23.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.23.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.24.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.24.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.25.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.25.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.26.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.26.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.27.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.27.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.28.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.28.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.29.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.29.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.30.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.30.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.31.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.31.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.32.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.32.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.33.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.33.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.34.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.34.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.35.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.35.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.36.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.36.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.37.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.37.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.38.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.38.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.39.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.39.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.40.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.40.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.41.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.41.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.42.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.42.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.43.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.43.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.44.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.44.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.45.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.45.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.46.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.46.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.47.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.47.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.48.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.48.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.49.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.49.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.50.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.50.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.51.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.51.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.52.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.52.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.53.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.53.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.54.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.54.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.55.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.55.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.56.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.56.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.57.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.57.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.58.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.58.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.59.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.59.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.60.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.60.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.61.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.61.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.62.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.62.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.63.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.63.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.64.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.64.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.65.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.65.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.66.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.66.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.67.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.67.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.68.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.68.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.69.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.69.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.70.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.70.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.71.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.71.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.72.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.72.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.73.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.73.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.74.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.74.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.75.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.75.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.76.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.76.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.77.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.77.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.78.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.78.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.79.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.79.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.80.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.80.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.81.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.81.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.82.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.82.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.83.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.83.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.84.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.84.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.85.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.85.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.86.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.86.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.87.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.87.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.88.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.88.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.89.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.89.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.90.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.90.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.91.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.91.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.92.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.92.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.93.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.93.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.94.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.94.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.95.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.95.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.96.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.96.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.97.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.97.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.98.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.98.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.99.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.99.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.100.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.100.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.101.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.101.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.102.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.102.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.103.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.103.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.104.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.104.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.105.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.105.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.106.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.106.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.107.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.107.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.108.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.108.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.109.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.109.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.110.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.110.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.111.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.111.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.112.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.112.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.113.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.113.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.114.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.114.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.115.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.115.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.116.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.116.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.117.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.117.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.118.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.118.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.119.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.119.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.120.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.120.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.121.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.121.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.122.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.122.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.123.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.123.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.124.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.124.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.125.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.125.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.126.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.126.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.127.gate_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.127.up_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.0.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.1.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.2.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.3.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.4.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.5.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.6.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.7.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.8.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.9.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.10.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.11.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.12.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.13.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.14.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.15.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.16.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.17.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.18.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.19.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.20.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.21.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.22.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.23.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.24.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.25.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.26.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.27.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.28.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.29.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.30.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.31.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.32.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.33.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.34.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.35.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.36.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.37.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.38.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.39.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.40.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.41.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.42.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.43.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.44.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.45.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.46.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.47.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.48.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.49.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.50.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.51.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.52.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.53.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.54.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.55.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.56.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.57.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.58.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.59.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.60.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.61.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.62.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.63.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.64.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.65.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.66.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.67.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.68.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.69.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.70.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.71.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.72.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.73.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.74.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.75.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.76.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.77.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.78.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.79.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.80.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.81.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.82.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.83.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.84.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.85.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.86.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.87.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.88.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.89.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.90.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.91.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.92.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.93.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.94.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.95.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.96.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.97.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.98.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.99.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.100.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.101.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.102.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.103.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.104.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.105.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.106.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.107.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.108.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.109.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.110.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.111.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.112.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.113.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.114.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.115.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.116.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.117.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.118.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.119.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.120.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.121.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.122.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.123.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.124.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.125.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.126.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.experts.127.down_proj.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.mlp.gate.weight": "model-00016-of-00041.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.mlp.shared_experts.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.mlp.shared_experts.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.mlp.gate.e_score_correction_bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.self_attn.q_proj.bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.self_attn.k_proj.bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.self_attn.v_proj.bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.0.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.0.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.1.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.1.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.2.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.2.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.3.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.3.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.4.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.4.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.5.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.5.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.6.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.6.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.7.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.7.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.8.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.8.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.9.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.9.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.10.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.10.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.11.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.11.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.12.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.12.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.13.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.13.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.14.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.14.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.15.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.15.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.16.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.16.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.17.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.17.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.18.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.18.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.19.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.19.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.20.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.20.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.21.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.21.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.22.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.22.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.23.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.23.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.24.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.24.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.25.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.25.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.26.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.26.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.27.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.27.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.28.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.28.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.29.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.29.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.30.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.30.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.31.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.31.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.32.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.32.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.33.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.33.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.34.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.34.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.35.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.35.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.36.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.36.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.37.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.37.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.38.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.38.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.39.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.39.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.40.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.40.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.41.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.41.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.42.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.42.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.43.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.43.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.44.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.44.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.45.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.45.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.46.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.46.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.47.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.47.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.48.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.48.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.49.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.49.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.50.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.50.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.51.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.51.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.52.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.52.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.53.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.53.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.54.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.54.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.55.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.55.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.56.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.56.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.57.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.57.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.58.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.58.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.59.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.59.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.60.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.60.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.61.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.61.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.62.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.62.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.63.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.63.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.64.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.64.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.65.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.65.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.66.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.66.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.67.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.67.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.68.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.68.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.69.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.69.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.70.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.70.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.71.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.71.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.72.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.72.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.73.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.73.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.74.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.74.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.75.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.75.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.76.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.76.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.77.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.77.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.78.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.78.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.79.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.79.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.80.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.80.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.81.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.81.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.82.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.82.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.83.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.83.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.84.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.84.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.85.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.85.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.86.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.86.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.87.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.87.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.88.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.88.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.89.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.89.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.90.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.90.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.91.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.91.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.92.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.92.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.93.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.93.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.94.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.94.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.95.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.95.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.96.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.96.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.97.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.97.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.98.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.98.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.99.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.99.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.100.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.100.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.101.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.101.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.102.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.102.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.103.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.103.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.104.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.104.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.105.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.105.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.106.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.106.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.107.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.107.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.108.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.108.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.109.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.109.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.110.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.110.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.111.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.111.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.112.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.112.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.113.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.113.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.114.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.114.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.115.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.115.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.116.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.116.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.117.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.117.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.118.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.118.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.119.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.119.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.120.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.120.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.121.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.121.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.122.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.122.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.123.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.123.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.124.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.124.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.125.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.125.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.126.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.126.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.127.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.127.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.0.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.1.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.2.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.3.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.4.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.5.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.6.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.7.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.8.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.9.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.10.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.11.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.12.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.13.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.14.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.15.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.16.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.17.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.18.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.19.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.20.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.21.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.22.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.23.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.24.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.25.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.26.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.27.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.28.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.29.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.30.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.31.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.32.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.33.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.34.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.35.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.36.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.37.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.38.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.39.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.40.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.41.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.42.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.43.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.44.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.45.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.46.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.47.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.48.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.49.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.50.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.51.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.52.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.53.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.54.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.55.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.56.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.57.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.58.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.59.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.60.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.61.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.62.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.63.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.64.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.65.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.66.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.67.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.68.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.69.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.70.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.71.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.72.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.73.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.74.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.75.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.76.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.77.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.78.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.79.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.80.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.81.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.82.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.83.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.84.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.85.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.86.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.87.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.88.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.89.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.90.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.91.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.92.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.93.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.94.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.95.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.96.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.97.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.98.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.99.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.100.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.101.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.102.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.103.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.104.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.105.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.106.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.107.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.108.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.109.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.110.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.111.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.112.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.113.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.114.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.115.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.116.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.117.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.118.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.119.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.120.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.121.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.122.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.123.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.124.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.125.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.126.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.experts.127.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.shared_experts.down_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.gate.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.shared_experts.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.mlp.gate.e_score_correction_bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.q_proj.bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.k_proj.bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.19.self_attn.v_proj.bias": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.0.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.0.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.1.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.1.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.2.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.2.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.3.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.3.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.4.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.4.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.5.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.5.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.6.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.6.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.7.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.7.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.8.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.8.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.9.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.9.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.10.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.10.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.11.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.11.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.12.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.12.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.13.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.13.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.14.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.14.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.15.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.15.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.16.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.16.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.17.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.17.up_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.18.gate_proj.weight": "model-00017-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.18.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.19.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.19.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.20.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.20.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.21.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.21.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.22.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.22.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.23.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.23.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.24.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.24.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.25.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.25.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.26.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.26.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.27.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.27.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.28.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.28.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.29.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.29.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.30.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.30.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.31.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.31.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.32.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.32.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.33.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.33.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.34.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.34.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.35.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.35.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.36.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.36.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.37.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.37.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.38.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.38.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.39.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.39.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.40.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.40.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.41.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.41.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.42.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.42.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.43.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.43.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.44.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.44.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.45.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.45.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.46.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.46.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.47.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.47.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.48.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.48.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.49.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.49.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.50.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.50.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.51.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.51.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.52.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.52.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.53.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.53.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.54.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.54.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.55.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.55.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.56.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.56.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.57.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.57.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.58.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.58.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.59.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.59.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.60.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.60.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.61.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.61.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.62.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.62.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.63.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.63.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.64.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.64.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.65.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.65.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.66.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.66.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.67.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.67.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.68.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.68.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.69.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.69.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.70.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.70.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.71.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.71.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.72.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.72.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.73.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.73.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.74.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.74.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.75.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.75.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.76.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.76.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.77.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.77.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.78.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.78.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.79.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.79.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.80.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.80.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.81.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.81.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.82.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.82.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.83.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.83.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.84.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.84.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.85.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.85.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.86.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.86.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.87.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.87.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.88.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.88.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.89.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.89.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.90.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.90.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.91.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.91.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.92.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.92.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.93.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.93.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.94.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.94.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.95.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.95.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.96.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.96.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.97.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.97.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.98.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.98.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.99.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.99.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.100.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.100.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.101.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.101.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.102.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.102.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.103.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.103.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.104.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.104.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.105.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.105.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.106.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.106.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.107.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.107.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.108.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.108.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.109.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.109.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.110.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.110.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.111.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.111.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.112.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.112.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.113.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.113.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.114.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.114.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.115.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.115.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.116.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.116.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.117.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.117.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.118.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.118.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.119.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.119.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.120.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.120.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.121.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.121.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.122.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.122.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.123.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.123.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.124.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.124.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.125.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.125.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.126.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.126.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.127.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.127.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.0.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.1.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.2.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.3.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.4.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.5.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.6.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.7.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.8.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.9.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.10.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.11.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.12.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.13.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.14.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.15.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.16.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.17.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.18.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.19.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.20.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.21.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.22.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.23.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.24.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.25.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.26.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.27.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.28.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.29.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.30.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.31.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.32.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.33.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.34.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.35.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.36.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.37.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.38.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.39.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.40.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.41.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.42.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.43.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.44.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.45.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.46.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.47.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.48.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.49.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.50.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.51.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.52.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.53.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.54.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.55.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.56.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.57.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.58.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.59.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.60.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.61.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.62.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.63.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.64.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.65.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.66.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.67.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.68.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.69.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.70.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.71.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.72.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.73.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.74.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.75.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.76.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.77.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.78.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.79.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.80.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.81.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.82.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.83.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.84.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.85.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.86.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.87.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.88.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.89.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.90.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.91.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.92.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.93.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.94.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.95.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.96.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.97.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.98.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.99.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.100.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.101.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.102.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.103.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.104.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.105.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.106.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.107.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.108.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.109.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.110.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.111.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.112.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.113.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.114.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.115.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.116.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.117.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.118.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.119.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.120.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.121.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.122.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.123.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.124.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.125.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.126.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.experts.127.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.gate.e_score_correction_bias": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.gate.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.shared_experts.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.mlp.shared_experts.down_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.q_proj.bias": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.k_proj.bias": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.v_proj.bias": "model-00018-of-00041.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.0.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.0.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.1.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.1.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.2.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.2.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.3.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.3.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.4.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.4.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.5.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.5.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.6.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.6.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.7.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.7.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.8.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.8.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.9.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.9.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.10.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.10.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.11.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.11.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.12.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.12.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.13.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.13.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.14.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.14.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.15.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.15.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.16.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.16.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.17.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.17.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.18.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.18.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.19.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.19.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.20.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.20.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.21.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.21.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.22.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.22.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.23.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.23.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.24.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.24.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.25.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.25.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.26.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.26.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.27.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.27.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.28.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.28.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.29.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.29.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.30.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.30.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.31.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.31.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.32.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.32.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.33.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.33.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.34.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.34.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.35.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.35.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.36.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.36.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.37.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.37.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.38.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.38.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.39.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.39.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.40.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.40.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.41.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.41.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.42.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.42.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.43.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.43.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.44.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.44.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.45.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.45.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.46.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.46.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.47.gate_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.47.up_proj.weight": "model-00018-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.48.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.48.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.49.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.49.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.50.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.50.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.51.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.51.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.52.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.52.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.53.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.53.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.54.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.54.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.55.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.55.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.56.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.56.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.57.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.57.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.58.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.58.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.59.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.59.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.60.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.60.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.61.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.61.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.62.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.62.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.63.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.63.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.64.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.64.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.65.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.65.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.66.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.66.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.67.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.67.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.68.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.68.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.69.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.69.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.70.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.70.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.71.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.71.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.72.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.72.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.73.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.73.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.74.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.74.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.75.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.75.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.76.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.76.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.77.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.77.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.78.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.78.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.79.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.79.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.80.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.80.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.81.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.81.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.82.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.82.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.83.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.83.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.84.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.84.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.85.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.85.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.86.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.86.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.87.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.87.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.88.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.88.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.89.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.89.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.90.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.90.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.91.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.91.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.92.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.92.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.93.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.93.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.94.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.94.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.95.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.95.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.96.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.96.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.97.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.97.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.98.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.98.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.99.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.99.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.100.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.100.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.101.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.101.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.102.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.102.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.103.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.103.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.104.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.104.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.105.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.105.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.106.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.106.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.107.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.107.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.108.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.108.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.109.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.109.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.110.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.110.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.111.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.111.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.112.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.112.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.113.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.113.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.114.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.114.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.115.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.115.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.116.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.116.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.117.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.117.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.118.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.118.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.119.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.119.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.120.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.120.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.121.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.121.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.122.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.122.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.123.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.123.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.124.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.124.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.125.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.125.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.126.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.126.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.127.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.127.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.0.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.1.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.2.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.3.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.4.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.5.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.6.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.7.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.8.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.9.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.10.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.11.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.12.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.13.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.14.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.15.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.16.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.17.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.18.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.19.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.20.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.21.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.22.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.23.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.24.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.25.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.26.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.27.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.28.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.29.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.30.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.31.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.32.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.33.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.34.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.35.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.36.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.37.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.38.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.39.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.40.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.41.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.42.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.43.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.44.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.45.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.46.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.47.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.48.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.49.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.50.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.51.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.52.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.53.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.54.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.55.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.56.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.57.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.58.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.59.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.60.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.61.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.62.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.63.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.64.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.65.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.66.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.67.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.68.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.69.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.70.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.71.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.72.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.73.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.74.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.75.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.76.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.77.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.78.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.79.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.80.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.81.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.82.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.83.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.84.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.85.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.86.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.87.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.88.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.89.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.90.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.91.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.92.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.93.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.94.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.95.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.96.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.97.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.98.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.99.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.100.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.101.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.102.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.103.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.104.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.105.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.106.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.107.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.108.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.109.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.110.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.111.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.112.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.113.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.114.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.115.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.116.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.117.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.118.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.119.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.120.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.121.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.122.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.123.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.124.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.125.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.126.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.experts.127.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.gate.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.shared_experts.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.shared_experts.down_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.mlp.gate.e_score_correction_bias": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.q_proj.bias": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.k_proj.bias": "model-00019-of-00041.safetensors", + "model.language_model.layers.21.self_attn.v_proj.bias": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.0.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.0.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.1.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.1.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.2.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.2.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.3.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.3.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.4.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.4.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.5.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.5.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.6.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.6.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.7.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.7.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.8.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.8.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.9.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.9.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.10.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.10.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.11.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.11.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.12.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.12.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.13.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.13.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.14.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.14.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.15.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.15.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.16.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.16.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.17.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.17.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.18.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.18.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.19.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.19.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.20.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.20.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.21.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.21.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.22.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.22.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.23.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.23.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.24.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.24.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.25.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.25.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.26.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.26.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.27.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.27.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.28.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.28.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.29.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.29.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.30.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.30.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.31.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.31.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.32.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.32.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.33.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.33.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.34.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.34.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.35.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.35.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.36.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.36.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.37.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.37.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.38.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.38.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.39.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.39.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.40.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.40.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.41.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.41.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.42.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.42.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.43.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.43.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.44.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.44.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.45.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.45.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.46.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.46.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.47.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.47.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.48.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.48.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.49.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.49.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.50.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.50.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.51.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.51.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.52.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.52.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.53.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.53.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.54.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.54.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.55.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.55.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.56.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.56.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.57.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.57.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.58.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.58.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.59.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.59.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.60.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.60.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.61.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.61.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.62.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.62.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.63.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.63.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.64.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.64.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.65.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.65.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.66.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.66.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.67.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.67.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.68.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.68.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.69.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.69.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.70.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.70.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.71.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.71.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.72.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.72.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.73.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.73.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.74.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.74.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.75.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.75.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.76.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.76.up_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.77.gate_proj.weight": "model-00019-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.77.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.78.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.78.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.79.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.79.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.80.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.80.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.81.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.81.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.82.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.82.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.83.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.83.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.84.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.84.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.85.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.85.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.86.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.86.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.87.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.87.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.88.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.88.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.89.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.89.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.90.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.90.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.91.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.91.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.92.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.92.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.93.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.93.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.94.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.94.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.95.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.95.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.96.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.96.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.97.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.97.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.98.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.98.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.99.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.99.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.100.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.100.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.101.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.101.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.102.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.102.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.103.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.103.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.104.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.104.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.105.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.105.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.106.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.106.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.107.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.107.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.108.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.108.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.109.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.109.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.110.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.110.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.111.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.111.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.112.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.112.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.113.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.113.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.114.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.114.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.115.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.115.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.116.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.116.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.117.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.117.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.118.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.118.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.119.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.119.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.120.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.120.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.121.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.121.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.122.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.122.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.123.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.123.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.124.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.124.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.125.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.125.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.126.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.126.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.127.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.127.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.0.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.1.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.2.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.3.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.4.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.5.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.6.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.7.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.8.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.9.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.10.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.11.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.12.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.13.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.14.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.15.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.16.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.17.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.18.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.19.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.20.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.21.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.22.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.23.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.24.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.25.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.26.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.27.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.28.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.29.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.30.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.31.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.32.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.33.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.34.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.35.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.36.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.37.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.38.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.39.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.40.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.41.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.42.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.43.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.44.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.45.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.46.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.47.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.48.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.49.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.50.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.51.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.52.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.53.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.54.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.55.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.56.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.57.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.58.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.59.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.60.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.61.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.62.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.63.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.64.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.65.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.66.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.67.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.68.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.69.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.70.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.71.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.72.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.73.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.74.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.75.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.76.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.77.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.78.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.79.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.80.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.81.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.82.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.83.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.84.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.85.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.86.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.87.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.88.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.89.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.90.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.91.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.92.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.93.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.94.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.95.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.96.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.97.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.98.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.99.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.100.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.101.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.102.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.103.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.104.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.105.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.106.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.107.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.108.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.109.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.110.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.111.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.112.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.113.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.114.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.115.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.116.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.117.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.118.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.119.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.120.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.121.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.122.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.123.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.124.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.125.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.126.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.experts.127.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.gate.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.shared_experts.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.q_proj.bias": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.k_proj.bias": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.self_attn.v_proj.bias": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.gate.e_score_correction_bias": "model-00020-of-00041.safetensors", + "model.language_model.layers.22.mlp.shared_experts.down_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.0.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.0.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.1.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.1.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.2.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.2.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.3.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.3.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.4.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.4.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.5.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.5.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.6.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.6.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.7.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.7.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.8.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.8.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.9.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.9.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.10.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.10.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.11.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.11.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.12.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.12.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.13.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.13.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.14.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.14.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.15.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.15.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.16.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.16.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.17.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.17.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.18.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.18.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.19.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.19.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.20.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.20.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.21.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.21.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.22.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.22.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.23.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.23.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.24.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.24.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.25.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.25.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.26.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.26.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.27.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.27.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.28.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.28.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.29.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.29.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.30.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.30.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.31.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.31.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.32.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.32.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.33.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.33.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.34.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.34.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.35.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.35.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.36.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.36.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.37.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.37.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.38.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.38.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.39.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.39.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.40.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.40.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.41.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.41.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.42.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.42.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.43.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.43.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.44.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.44.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.45.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.45.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.46.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.46.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.47.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.47.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.48.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.48.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.49.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.49.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.50.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.50.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.51.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.51.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.52.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.52.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.53.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.53.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.54.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.54.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.55.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.55.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.56.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.56.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.57.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.57.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.58.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.58.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.59.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.59.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.60.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.60.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.61.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.61.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.62.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.62.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.63.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.63.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.64.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.64.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.65.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.65.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.66.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.66.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.67.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.67.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.68.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.68.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.69.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.69.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.70.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.70.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.71.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.71.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.72.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.72.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.73.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.73.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.74.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.74.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.75.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.75.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.76.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.76.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.77.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.77.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.78.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.78.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.79.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.79.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.80.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.80.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.81.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.81.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.82.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.82.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.83.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.83.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.84.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.84.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.85.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.85.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.86.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.86.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.87.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.87.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.88.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.88.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.89.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.89.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.90.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.90.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.91.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.91.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.92.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.92.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.93.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.93.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.94.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.94.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.95.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.95.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.96.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.96.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.97.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.97.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.98.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.98.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.99.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.99.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.100.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.100.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.101.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.101.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.102.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.102.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.103.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.103.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.104.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.104.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.105.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.105.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.106.gate_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.106.up_proj.weight": "model-00020-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.107.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.107.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.108.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.108.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.109.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.109.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.110.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.110.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.111.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.111.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.112.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.112.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.113.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.113.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.114.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.114.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.115.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.115.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.116.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.116.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.117.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.117.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.118.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.118.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.119.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.119.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.120.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.120.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.121.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.121.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.122.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.122.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.123.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.123.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.124.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.124.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.125.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.125.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.126.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.126.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.127.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.127.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.0.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.1.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.2.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.3.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.4.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.5.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.6.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.7.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.8.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.9.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.10.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.11.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.12.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.13.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.14.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.15.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.16.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.17.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.18.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.19.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.20.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.21.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.22.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.23.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.24.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.25.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.26.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.27.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.28.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.29.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.30.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.31.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.32.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.33.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.34.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.35.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.36.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.37.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.38.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.39.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.40.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.41.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.42.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.43.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.44.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.45.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.46.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.47.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.48.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.49.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.50.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.51.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.52.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.53.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.54.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.55.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.56.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.57.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.58.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.59.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.60.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.61.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.62.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.63.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.64.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.65.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.66.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.67.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.68.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.69.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.70.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.71.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.72.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.73.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.74.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.75.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.76.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.77.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.78.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.79.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.80.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.81.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.82.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.83.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.84.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.85.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.86.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.87.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.88.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.89.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.90.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.91.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.92.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.93.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.94.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.95.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.96.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.97.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.98.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.99.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.100.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.101.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.102.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.103.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.104.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.105.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.106.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.107.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.108.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.109.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.110.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.111.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.112.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.113.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.114.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.115.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.116.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.117.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.118.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.119.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.120.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.121.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.122.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.123.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.124.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.125.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.126.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.experts.127.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.shared_experts.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.gate.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.q_proj.bias": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.k_proj.bias": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.self_attn.v_proj.bias": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.shared_experts.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.23.mlp.gate.e_score_correction_bias": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.0.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.0.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.1.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.1.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.2.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.2.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.3.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.3.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.4.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.4.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.5.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.5.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.6.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.6.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.7.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.7.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.8.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.8.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.9.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.9.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.10.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.10.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.11.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.11.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.12.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.12.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.13.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.13.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.14.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.14.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.15.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.15.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.16.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.16.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.17.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.17.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.18.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.18.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.19.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.19.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.20.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.20.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.21.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.21.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.22.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.22.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.23.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.23.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.24.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.24.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.25.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.25.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.26.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.26.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.27.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.27.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.28.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.28.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.29.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.29.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.30.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.30.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.31.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.31.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.32.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.32.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.33.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.33.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.34.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.34.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.35.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.35.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.36.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.36.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.37.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.37.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.38.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.38.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.39.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.39.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.40.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.40.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.41.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.41.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.42.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.42.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.43.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.43.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.44.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.44.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.45.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.45.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.46.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.46.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.47.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.47.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.48.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.48.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.49.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.49.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.50.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.50.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.51.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.51.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.52.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.52.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.53.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.53.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.54.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.54.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.55.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.55.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.56.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.56.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.57.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.57.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.58.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.58.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.59.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.59.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.60.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.60.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.61.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.61.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.62.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.62.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.63.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.63.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.64.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.64.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.65.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.65.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.66.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.66.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.67.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.67.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.68.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.68.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.69.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.69.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.70.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.70.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.71.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.71.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.72.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.72.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.73.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.73.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.74.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.74.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.75.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.75.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.76.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.76.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.77.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.77.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.78.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.78.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.79.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.79.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.80.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.80.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.81.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.81.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.82.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.82.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.83.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.83.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.84.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.84.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.85.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.85.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.86.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.86.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.87.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.87.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.88.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.88.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.89.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.89.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.90.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.90.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.91.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.91.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.92.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.92.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.93.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.93.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.94.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.94.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.95.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.95.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.96.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.96.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.97.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.97.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.98.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.98.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.99.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.99.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.100.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.100.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.101.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.101.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.102.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.102.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.103.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.103.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.104.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.104.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.105.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.105.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.106.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.106.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.107.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.107.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.108.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.108.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.109.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.109.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.110.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.110.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.111.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.111.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.112.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.112.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.113.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.113.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.114.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.114.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.115.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.115.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.116.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.116.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.117.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.117.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.118.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.118.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.119.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.119.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.120.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.120.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.121.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.121.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.122.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.122.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.123.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.123.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.124.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.124.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.125.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.125.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.126.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.126.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.127.gate_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.127.up_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.0.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.1.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.2.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.3.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.4.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.5.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.6.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.7.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.8.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.9.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.10.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.11.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.12.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.13.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.14.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.15.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.16.down_proj.weight": "model-00021-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.17.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.18.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.19.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.20.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.21.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.22.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.23.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.24.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.25.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.26.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.27.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.28.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.29.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.30.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.31.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.32.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.33.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.34.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.35.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.36.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.37.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.38.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.39.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.40.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.41.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.42.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.43.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.44.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.45.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.46.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.47.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.48.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.49.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.50.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.51.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.52.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.53.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.54.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.55.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.56.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.57.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.58.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.59.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.60.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.61.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.62.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.63.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.64.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.65.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.66.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.67.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.68.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.69.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.70.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.71.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.72.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.73.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.74.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.75.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.76.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.77.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.78.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.79.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.80.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.81.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.82.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.83.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.84.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.85.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.86.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.87.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.88.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.89.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.90.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.91.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.92.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.93.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.94.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.95.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.96.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.97.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.98.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.99.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.100.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.101.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.102.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.103.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.104.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.105.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.106.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.107.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.108.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.109.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.110.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.111.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.112.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.113.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.114.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.115.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.116.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.117.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.118.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.119.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.120.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.121.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.122.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.123.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.124.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.125.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.126.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.experts.127.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.shared_experts.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.gate.e_score_correction_bias": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.shared_experts.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.mlp.gate.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.q_proj.bias": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.k_proj.bias": "model-00022-of-00041.safetensors", + "model.language_model.layers.24.self_attn.v_proj.bias": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.0.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.0.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.1.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.1.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.2.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.2.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.3.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.3.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.4.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.4.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.5.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.5.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.6.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.6.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.7.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.7.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.8.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.8.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.9.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.9.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.10.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.10.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.11.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.11.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.12.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.12.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.13.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.13.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.14.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.14.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.15.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.15.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.16.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.16.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.17.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.17.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.18.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.18.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.19.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.19.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.20.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.20.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.21.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.21.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.22.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.22.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.23.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.23.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.24.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.24.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.25.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.25.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.26.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.26.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.27.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.27.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.28.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.28.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.29.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.29.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.30.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.30.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.31.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.31.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.32.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.32.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.33.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.33.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.34.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.34.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.35.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.35.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.36.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.36.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.37.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.37.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.38.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.38.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.39.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.39.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.40.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.40.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.41.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.41.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.42.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.42.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.43.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.43.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.44.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.44.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.45.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.45.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.46.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.46.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.47.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.47.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.48.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.48.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.49.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.49.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.50.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.50.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.51.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.51.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.52.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.52.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.53.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.53.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.54.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.54.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.55.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.55.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.56.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.56.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.57.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.57.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.58.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.58.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.59.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.59.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.60.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.60.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.61.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.61.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.62.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.62.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.63.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.63.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.64.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.64.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.65.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.65.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.66.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.66.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.67.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.67.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.68.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.68.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.69.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.69.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.70.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.70.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.71.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.71.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.72.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.72.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.73.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.73.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.74.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.74.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.75.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.75.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.76.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.76.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.77.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.77.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.78.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.78.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.79.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.79.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.80.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.80.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.81.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.81.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.82.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.82.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.83.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.83.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.84.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.84.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.85.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.85.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.86.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.86.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.87.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.87.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.88.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.88.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.89.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.89.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.90.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.90.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.91.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.91.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.92.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.92.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.93.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.93.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.94.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.94.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.95.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.95.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.96.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.96.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.97.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.97.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.98.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.98.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.99.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.99.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.100.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.100.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.101.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.101.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.102.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.102.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.103.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.103.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.104.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.104.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.105.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.105.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.106.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.106.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.107.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.107.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.108.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.108.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.109.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.109.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.110.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.110.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.111.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.111.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.112.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.112.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.113.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.113.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.114.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.114.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.115.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.115.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.116.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.116.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.117.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.117.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.118.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.118.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.119.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.119.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.120.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.120.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.121.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.121.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.122.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.122.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.123.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.123.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.124.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.124.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.125.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.125.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.126.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.126.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.127.gate_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.127.up_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.0.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.1.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.2.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.3.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.4.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.5.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.6.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.7.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.8.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.9.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.10.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.11.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.12.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.13.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.14.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.15.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.16.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.17.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.18.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.19.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.20.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.21.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.22.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.23.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.24.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.25.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.26.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.27.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.28.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.29.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.30.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.31.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.32.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.33.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.34.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.35.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.36.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.37.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.38.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.39.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.40.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.41.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.42.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.43.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.44.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.45.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.46.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.47.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.48.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.49.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.50.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.51.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.52.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.53.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.54.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.55.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.56.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.57.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.58.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.59.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.60.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.61.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.62.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.63.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.64.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.65.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.66.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.67.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.68.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.69.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.70.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.71.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.72.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.73.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.74.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.75.down_proj.weight": "model-00022-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.76.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.77.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.78.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.79.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.80.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.81.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.82.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.83.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.84.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.85.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.86.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.87.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.88.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.89.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.90.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.91.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.92.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.93.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.94.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.95.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.96.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.97.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.98.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.99.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.100.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.101.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.102.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.103.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.104.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.105.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.106.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.107.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.108.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.109.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.110.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.111.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.112.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.113.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.114.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.115.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.116.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.117.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.118.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.119.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.120.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.121.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.122.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.123.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.124.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.125.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.126.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.experts.127.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.shared_experts.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.shared_experts.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.gate.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.q_proj.bias": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.k_proj.bias": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.self_attn.v_proj.bias": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.mlp.gate.e_score_correction_bias": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.0.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.0.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.1.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.1.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.2.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.2.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.3.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.3.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.4.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.4.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.5.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.5.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.6.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.6.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.7.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.7.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.8.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.8.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.9.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.9.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.10.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.10.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.11.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.11.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.12.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.12.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.13.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.13.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.14.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.14.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.15.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.15.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.16.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.16.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.17.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.17.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.18.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.18.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.19.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.19.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.20.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.20.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.21.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.21.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.22.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.22.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.23.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.23.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.24.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.24.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.25.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.25.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.26.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.26.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.27.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.27.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.28.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.28.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.29.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.29.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.30.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.30.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.31.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.31.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.32.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.32.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.33.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.33.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.34.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.34.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.35.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.35.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.36.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.36.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.37.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.37.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.38.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.38.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.39.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.39.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.40.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.40.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.41.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.41.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.42.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.42.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.43.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.43.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.44.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.44.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.45.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.45.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.46.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.46.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.47.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.47.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.48.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.48.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.49.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.49.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.50.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.50.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.51.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.51.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.52.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.52.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.53.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.53.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.54.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.54.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.55.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.55.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.56.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.56.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.57.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.57.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.58.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.58.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.59.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.59.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.60.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.60.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.61.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.61.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.62.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.62.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.63.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.63.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.64.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.64.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.65.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.65.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.66.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.66.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.67.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.67.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.68.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.68.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.69.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.69.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.70.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.70.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.71.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.71.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.72.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.72.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.73.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.73.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.74.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.74.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.75.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.75.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.76.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.76.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.77.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.77.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.78.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.78.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.79.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.79.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.80.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.80.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.81.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.81.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.82.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.82.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.83.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.83.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.84.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.84.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.85.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.85.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.86.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.86.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.87.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.87.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.88.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.88.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.89.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.89.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.90.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.90.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.91.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.91.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.92.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.92.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.93.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.93.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.94.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.94.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.95.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.95.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.96.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.96.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.97.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.97.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.98.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.98.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.99.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.99.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.100.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.100.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.101.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.101.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.102.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.102.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.103.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.103.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.104.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.104.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.105.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.105.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.106.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.106.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.107.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.107.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.108.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.108.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.109.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.109.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.110.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.110.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.111.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.111.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.112.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.112.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.113.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.113.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.114.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.114.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.115.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.115.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.116.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.116.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.117.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.117.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.118.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.118.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.119.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.119.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.120.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.120.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.121.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.121.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.122.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.122.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.123.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.123.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.124.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.124.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.125.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.125.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.126.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.126.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.127.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.127.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.0.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.1.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.2.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.3.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.4.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.5.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.6.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.7.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.8.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.9.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.10.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.11.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.12.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.13.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.14.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.15.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.16.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.17.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.18.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.19.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.20.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.21.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.22.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.23.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.24.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.25.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.26.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.27.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.28.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.29.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.30.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.31.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.32.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.33.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.34.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.35.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.36.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.37.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.38.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.39.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.40.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.41.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.42.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.43.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.44.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.45.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.46.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.47.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.48.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.49.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.50.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.51.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.52.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.53.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.54.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.55.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.56.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.57.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.58.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.59.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.60.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.61.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.62.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.63.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.64.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.65.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.66.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.67.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.68.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.69.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.70.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.71.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.72.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.73.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.74.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.75.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.76.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.77.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.78.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.79.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.80.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.81.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.82.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.83.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.84.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.85.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.86.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.87.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.88.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.89.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.90.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.91.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.92.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.93.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.94.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.95.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.96.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.97.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.98.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.99.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.100.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.101.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.102.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.103.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.104.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.105.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.106.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.107.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.108.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.109.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.110.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.111.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.112.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.113.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.114.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.115.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.116.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.117.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.118.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.119.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.120.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.121.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.122.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.123.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.124.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.125.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.126.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.experts.127.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.shared_experts.up_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.shared_experts.down_proj.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.mlp.gate.weight": "model-00023-of-00041.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.mlp.gate.e_score_correction_bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.self_attn.q_proj.bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.self_attn.k_proj.bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.26.self_attn.v_proj.bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.0.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.0.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.1.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.1.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.2.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.2.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.3.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.3.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.4.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.4.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.5.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.5.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.6.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.6.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.7.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.7.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.8.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.8.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.9.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.9.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.10.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.10.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.11.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.11.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.12.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.12.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.13.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.13.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.14.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.14.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.15.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.15.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.16.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.16.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.17.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.17.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.18.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.18.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.19.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.19.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.20.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.20.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.21.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.21.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.22.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.22.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.23.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.23.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.24.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.24.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.25.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.25.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.26.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.26.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.27.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.27.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.28.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.28.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.29.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.29.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.30.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.30.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.31.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.31.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.32.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.32.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.33.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.33.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.34.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.34.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.35.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.35.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.36.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.36.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.37.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.37.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.38.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.38.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.39.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.39.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.40.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.40.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.41.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.41.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.42.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.42.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.43.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.43.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.44.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.44.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.45.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.45.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.46.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.46.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.47.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.47.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.48.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.48.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.49.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.49.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.50.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.50.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.51.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.51.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.52.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.52.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.53.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.53.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.54.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.54.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.55.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.55.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.56.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.56.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.57.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.57.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.58.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.58.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.59.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.59.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.60.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.60.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.61.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.61.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.62.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.62.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.63.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.63.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.64.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.64.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.65.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.65.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.66.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.66.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.67.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.67.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.68.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.68.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.69.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.69.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.70.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.70.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.71.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.71.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.72.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.72.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.73.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.73.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.74.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.74.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.75.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.75.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.76.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.76.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.77.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.77.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.78.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.78.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.79.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.79.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.80.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.80.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.81.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.81.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.82.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.82.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.83.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.83.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.84.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.84.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.85.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.85.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.86.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.86.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.87.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.87.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.88.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.88.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.89.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.89.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.90.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.90.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.91.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.91.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.92.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.92.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.93.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.93.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.94.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.94.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.95.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.95.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.96.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.96.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.97.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.97.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.98.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.98.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.99.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.99.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.100.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.100.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.101.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.101.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.102.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.102.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.103.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.103.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.104.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.104.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.105.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.105.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.106.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.106.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.107.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.107.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.108.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.108.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.109.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.109.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.110.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.110.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.111.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.111.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.112.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.112.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.113.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.113.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.114.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.114.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.115.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.115.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.116.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.116.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.117.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.117.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.118.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.118.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.119.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.119.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.120.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.120.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.121.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.121.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.122.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.122.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.123.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.123.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.124.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.124.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.125.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.125.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.126.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.126.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.127.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.127.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.0.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.1.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.2.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.3.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.4.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.5.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.6.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.7.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.8.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.9.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.10.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.11.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.12.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.13.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.14.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.15.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.16.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.17.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.18.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.19.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.20.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.21.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.22.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.23.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.24.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.25.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.26.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.27.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.28.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.29.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.30.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.31.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.32.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.33.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.34.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.35.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.36.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.37.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.38.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.39.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.40.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.41.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.42.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.43.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.44.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.45.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.46.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.47.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.48.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.49.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.50.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.51.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.52.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.53.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.54.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.55.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.56.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.57.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.58.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.59.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.60.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.61.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.62.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.63.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.64.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.65.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.66.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.67.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.68.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.69.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.70.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.71.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.72.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.73.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.74.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.75.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.76.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.77.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.78.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.79.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.80.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.81.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.82.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.83.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.84.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.85.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.86.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.87.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.88.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.89.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.90.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.91.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.92.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.93.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.94.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.95.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.96.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.97.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.98.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.99.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.100.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.101.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.102.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.103.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.104.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.105.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.106.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.107.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.108.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.109.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.110.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.111.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.112.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.113.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.114.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.115.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.116.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.117.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.118.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.119.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.120.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.121.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.122.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.123.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.124.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.125.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.126.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.experts.127.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.gate.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.shared_experts.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.shared_experts.down_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.mlp.gate.e_score_correction_bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.q_proj.bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.k_proj.bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.27.self_attn.v_proj.bias": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.0.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.0.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.1.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.1.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.2.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.2.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.3.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.3.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.4.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.4.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.5.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.5.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.6.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.6.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.7.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.7.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.8.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.8.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.9.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.9.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.10.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.10.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.11.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.11.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.12.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.12.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.13.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.13.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.14.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.14.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.15.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.15.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.16.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.16.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.17.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.17.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.18.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.18.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.19.gate_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.19.up_proj.weight": "model-00024-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.20.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.20.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.21.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.21.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.22.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.22.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.23.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.23.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.24.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.24.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.25.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.25.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.26.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.26.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.27.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.27.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.28.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.28.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.29.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.29.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.30.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.30.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.31.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.31.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.32.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.32.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.33.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.33.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.34.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.34.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.35.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.35.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.36.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.36.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.37.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.37.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.38.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.38.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.39.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.39.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.40.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.40.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.41.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.41.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.42.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.42.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.43.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.43.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.44.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.44.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.45.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.45.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.46.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.46.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.47.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.47.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.48.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.48.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.49.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.49.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.50.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.50.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.51.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.51.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.52.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.52.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.53.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.53.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.54.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.54.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.55.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.55.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.56.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.56.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.57.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.57.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.58.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.58.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.59.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.59.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.60.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.60.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.61.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.61.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.62.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.62.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.63.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.63.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.64.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.64.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.65.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.65.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.66.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.66.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.67.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.67.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.68.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.68.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.69.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.69.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.70.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.70.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.71.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.71.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.72.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.72.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.73.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.73.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.74.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.74.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.75.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.75.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.76.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.76.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.77.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.77.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.78.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.78.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.79.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.79.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.80.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.80.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.81.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.81.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.82.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.82.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.83.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.83.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.84.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.84.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.85.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.85.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.86.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.86.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.87.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.87.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.88.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.88.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.89.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.89.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.90.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.90.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.91.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.91.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.92.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.92.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.93.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.93.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.94.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.94.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.95.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.95.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.96.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.96.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.97.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.97.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.98.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.98.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.99.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.99.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.100.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.100.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.101.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.101.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.102.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.102.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.103.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.103.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.104.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.104.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.105.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.105.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.106.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.106.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.107.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.107.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.108.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.108.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.109.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.109.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.110.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.110.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.111.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.111.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.112.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.112.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.113.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.113.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.114.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.114.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.115.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.115.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.116.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.116.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.117.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.117.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.118.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.118.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.119.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.119.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.120.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.120.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.121.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.121.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.122.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.122.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.123.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.123.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.124.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.124.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.125.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.125.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.126.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.126.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.127.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.127.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.0.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.1.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.2.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.3.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.4.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.5.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.6.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.7.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.8.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.9.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.10.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.11.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.12.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.13.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.14.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.15.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.16.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.17.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.18.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.19.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.20.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.21.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.22.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.23.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.24.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.25.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.26.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.27.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.28.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.29.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.30.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.31.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.32.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.33.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.34.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.35.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.36.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.37.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.38.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.39.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.40.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.41.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.42.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.43.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.44.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.45.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.46.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.47.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.48.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.49.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.50.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.51.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.52.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.53.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.54.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.55.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.56.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.57.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.58.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.59.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.60.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.61.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.62.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.63.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.64.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.65.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.66.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.67.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.68.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.69.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.70.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.71.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.72.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.73.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.74.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.75.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.76.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.77.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.78.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.79.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.80.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.81.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.82.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.83.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.84.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.85.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.86.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.87.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.88.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.89.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.90.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.91.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.92.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.93.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.94.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.95.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.96.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.97.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.98.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.99.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.100.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.101.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.102.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.103.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.104.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.105.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.106.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.107.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.108.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.109.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.110.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.111.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.112.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.113.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.114.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.115.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.116.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.117.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.118.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.119.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.120.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.121.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.122.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.123.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.124.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.125.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.126.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.experts.127.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.gate.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.shared_experts.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.shared_experts.down_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.q_proj.bias": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.k_proj.bias": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.self_attn.v_proj.bias": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.28.mlp.gate.e_score_correction_bias": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.0.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.0.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.1.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.1.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.2.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.2.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.3.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.3.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.4.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.4.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.5.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.5.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.6.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.6.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.7.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.7.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.8.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.8.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.9.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.9.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.10.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.10.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.11.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.11.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.12.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.12.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.13.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.13.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.14.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.14.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.15.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.15.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.16.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.16.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.17.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.17.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.18.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.18.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.19.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.19.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.20.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.20.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.21.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.21.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.22.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.22.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.23.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.23.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.24.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.24.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.25.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.25.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.26.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.26.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.27.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.27.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.28.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.28.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.29.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.29.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.30.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.30.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.31.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.31.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.32.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.32.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.33.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.33.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.34.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.34.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.35.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.35.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.36.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.36.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.37.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.37.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.38.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.38.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.39.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.39.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.40.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.40.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.41.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.41.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.42.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.42.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.43.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.43.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.44.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.44.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.45.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.45.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.46.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.46.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.47.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.47.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.48.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.48.up_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.49.gate_proj.weight": "model-00025-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.49.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.50.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.50.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.51.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.51.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.52.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.52.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.53.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.53.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.54.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.54.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.55.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.55.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.56.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.56.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.57.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.57.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.58.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.58.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.59.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.59.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.60.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.60.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.61.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.61.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.62.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.62.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.63.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.63.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.64.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.64.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.65.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.65.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.66.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.66.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.67.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.67.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.68.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.68.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.69.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.69.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.70.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.70.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.71.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.71.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.72.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.72.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.73.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.73.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.74.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.74.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.75.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.75.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.76.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.76.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.77.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.77.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.78.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.78.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.79.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.79.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.80.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.80.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.81.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.81.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.82.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.82.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.83.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.83.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.84.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.84.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.85.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.85.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.86.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.86.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.87.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.87.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.88.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.88.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.89.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.89.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.90.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.90.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.91.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.91.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.92.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.92.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.93.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.93.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.94.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.94.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.95.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.95.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.96.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.96.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.97.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.97.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.98.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.98.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.99.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.99.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.100.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.100.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.101.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.101.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.102.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.102.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.103.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.103.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.104.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.104.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.105.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.105.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.106.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.106.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.107.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.107.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.108.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.108.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.109.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.109.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.110.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.110.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.111.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.111.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.112.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.112.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.113.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.113.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.114.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.114.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.115.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.115.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.116.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.116.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.117.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.117.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.118.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.118.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.119.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.119.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.120.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.120.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.121.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.121.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.122.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.122.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.123.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.123.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.124.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.124.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.125.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.125.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.126.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.126.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.127.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.127.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.0.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.1.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.2.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.3.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.4.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.5.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.6.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.7.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.8.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.9.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.10.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.11.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.12.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.13.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.14.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.15.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.16.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.17.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.18.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.19.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.20.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.21.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.22.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.23.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.24.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.25.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.26.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.27.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.28.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.29.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.30.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.31.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.32.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.33.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.34.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.35.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.36.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.37.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.38.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.39.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.40.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.41.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.42.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.43.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.44.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.45.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.46.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.47.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.48.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.49.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.50.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.51.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.52.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.53.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.54.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.55.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.56.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.57.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.58.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.59.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.60.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.61.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.62.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.63.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.64.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.65.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.66.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.67.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.68.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.69.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.70.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.71.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.72.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.73.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.74.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.75.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.76.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.77.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.78.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.79.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.80.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.81.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.82.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.83.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.84.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.85.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.86.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.87.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.88.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.89.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.90.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.91.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.92.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.93.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.94.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.95.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.96.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.97.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.98.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.99.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.100.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.101.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.102.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.103.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.104.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.105.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.106.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.107.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.108.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.109.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.110.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.111.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.112.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.113.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.114.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.115.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.116.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.117.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.118.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.119.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.120.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.121.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.122.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.123.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.124.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.125.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.126.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.experts.127.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.gate.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.gate.e_score_correction_bias": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.shared_experts.down_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.mlp.shared_experts.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.q_proj.bias": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.k_proj.bias": "model-00026-of-00041.safetensors", + "model.language_model.layers.29.self_attn.v_proj.bias": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.0.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.0.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.1.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.1.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.2.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.2.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.3.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.3.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.4.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.4.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.5.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.5.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.6.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.6.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.7.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.7.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.8.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.8.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.9.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.9.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.10.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.10.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.11.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.11.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.12.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.12.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.13.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.13.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.14.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.14.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.15.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.15.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.16.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.16.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.17.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.17.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.18.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.18.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.19.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.19.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.20.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.20.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.21.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.21.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.22.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.22.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.23.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.23.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.24.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.24.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.25.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.25.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.26.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.26.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.27.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.27.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.28.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.28.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.29.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.29.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.30.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.30.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.31.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.31.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.32.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.32.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.33.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.33.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.34.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.34.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.35.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.35.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.36.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.36.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.37.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.37.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.38.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.38.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.39.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.39.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.40.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.40.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.41.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.41.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.42.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.42.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.43.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.43.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.44.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.44.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.45.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.45.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.46.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.46.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.47.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.47.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.48.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.48.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.49.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.49.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.50.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.50.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.51.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.51.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.52.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.52.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.53.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.53.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.54.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.54.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.55.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.55.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.56.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.56.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.57.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.57.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.58.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.58.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.59.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.59.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.60.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.60.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.61.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.61.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.62.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.62.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.63.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.63.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.64.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.64.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.65.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.65.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.66.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.66.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.67.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.67.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.68.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.68.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.69.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.69.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.70.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.70.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.71.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.71.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.72.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.72.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.73.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.73.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.74.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.74.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.75.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.75.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.76.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.76.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.77.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.77.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.78.gate_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.78.up_proj.weight": "model-00026-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.79.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.79.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.80.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.80.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.81.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.81.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.82.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.82.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.83.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.83.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.84.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.84.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.85.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.85.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.86.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.86.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.87.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.87.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.88.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.88.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.89.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.89.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.90.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.90.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.91.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.91.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.92.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.92.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.93.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.93.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.94.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.94.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.95.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.95.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.96.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.96.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.97.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.97.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.98.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.98.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.99.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.99.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.100.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.100.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.101.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.101.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.102.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.102.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.103.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.103.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.104.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.104.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.105.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.105.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.106.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.106.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.107.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.107.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.108.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.108.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.109.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.109.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.110.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.110.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.111.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.111.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.112.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.112.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.113.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.113.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.114.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.114.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.115.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.115.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.116.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.116.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.117.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.117.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.118.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.118.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.119.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.119.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.120.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.120.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.121.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.121.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.122.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.122.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.123.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.123.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.124.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.124.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.125.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.125.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.126.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.126.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.127.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.127.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.0.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.1.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.2.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.3.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.4.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.5.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.6.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.7.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.8.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.9.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.10.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.11.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.12.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.13.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.14.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.15.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.16.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.17.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.18.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.19.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.20.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.21.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.22.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.23.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.24.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.25.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.26.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.27.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.28.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.29.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.30.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.31.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.32.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.33.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.34.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.35.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.36.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.37.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.38.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.39.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.40.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.41.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.42.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.43.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.44.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.45.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.46.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.47.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.48.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.49.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.50.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.51.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.52.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.53.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.54.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.55.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.56.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.57.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.58.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.59.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.60.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.61.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.62.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.63.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.64.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.65.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.66.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.67.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.68.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.69.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.70.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.71.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.72.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.73.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.74.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.75.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.76.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.77.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.78.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.79.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.80.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.81.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.82.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.83.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.84.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.85.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.86.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.87.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.88.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.89.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.90.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.91.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.92.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.93.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.94.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.95.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.96.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.97.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.98.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.99.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.100.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.101.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.102.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.103.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.104.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.105.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.106.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.107.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.108.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.109.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.110.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.111.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.112.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.113.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.114.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.115.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.116.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.117.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.118.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.119.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.120.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.121.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.122.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.123.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.124.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.125.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.126.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.experts.127.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.gate.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.shared_experts.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.shared_experts.down_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.q_proj.bias": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.k_proj.bias": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.v_proj.bias": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.mlp.gate.e_score_correction_bias": "model-00027-of-00041.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.0.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.0.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.1.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.1.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.2.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.2.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.3.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.3.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.4.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.4.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.5.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.5.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.6.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.6.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.7.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.7.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.8.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.8.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.9.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.9.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.10.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.10.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.11.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.11.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.12.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.12.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.13.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.13.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.14.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.14.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.15.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.15.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.16.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.16.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.17.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.17.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.18.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.18.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.19.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.19.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.20.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.20.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.21.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.21.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.22.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.22.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.23.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.23.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.24.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.24.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.25.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.25.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.26.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.26.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.27.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.27.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.28.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.28.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.29.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.29.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.30.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.30.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.31.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.31.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.32.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.32.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.33.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.33.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.34.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.34.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.35.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.35.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.36.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.36.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.37.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.37.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.38.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.38.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.39.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.39.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.40.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.40.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.41.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.41.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.42.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.42.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.43.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.43.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.44.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.44.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.45.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.45.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.46.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.46.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.47.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.47.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.48.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.48.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.49.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.49.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.50.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.50.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.51.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.51.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.52.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.52.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.53.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.53.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.54.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.54.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.55.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.55.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.56.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.56.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.57.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.57.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.58.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.58.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.59.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.59.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.60.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.60.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.61.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.61.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.62.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.62.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.63.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.63.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.64.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.64.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.65.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.65.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.66.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.66.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.67.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.67.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.68.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.68.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.69.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.69.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.70.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.70.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.71.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.71.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.72.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.72.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.73.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.73.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.74.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.74.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.75.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.75.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.76.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.76.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.77.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.77.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.78.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.78.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.79.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.79.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.80.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.80.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.81.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.81.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.82.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.82.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.83.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.83.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.84.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.84.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.85.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.85.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.86.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.86.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.87.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.87.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.88.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.88.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.89.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.89.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.90.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.90.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.91.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.91.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.92.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.92.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.93.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.93.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.94.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.94.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.95.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.95.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.96.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.96.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.97.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.97.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.98.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.98.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.99.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.99.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.100.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.100.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.101.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.101.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.102.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.102.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.103.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.103.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.104.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.104.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.105.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.105.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.106.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.106.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.107.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.107.up_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.108.gate_proj.weight": "model-00027-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.108.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.109.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.109.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.110.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.110.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.111.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.111.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.112.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.112.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.113.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.113.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.114.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.114.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.115.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.115.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.116.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.116.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.117.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.117.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.118.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.118.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.119.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.119.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.120.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.120.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.121.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.121.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.122.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.122.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.123.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.123.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.124.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.124.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.125.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.125.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.126.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.126.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.127.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.127.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.0.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.1.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.2.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.3.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.4.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.5.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.6.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.7.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.8.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.9.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.10.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.11.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.12.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.13.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.14.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.15.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.16.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.17.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.18.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.19.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.20.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.21.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.22.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.23.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.24.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.25.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.26.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.27.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.28.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.29.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.30.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.31.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.32.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.33.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.34.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.35.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.36.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.37.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.38.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.39.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.40.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.41.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.42.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.43.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.44.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.45.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.46.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.47.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.48.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.49.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.50.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.51.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.52.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.53.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.54.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.55.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.56.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.57.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.58.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.59.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.60.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.61.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.62.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.63.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.64.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.65.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.66.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.67.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.68.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.69.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.70.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.71.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.72.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.73.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.74.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.75.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.76.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.77.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.78.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.79.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.80.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.81.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.82.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.83.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.84.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.85.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.86.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.87.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.88.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.89.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.90.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.91.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.92.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.93.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.94.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.95.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.96.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.97.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.98.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.99.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.100.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.101.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.102.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.103.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.104.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.105.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.106.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.107.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.108.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.109.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.110.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.111.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.112.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.113.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.114.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.115.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.116.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.117.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.118.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.119.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.120.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.121.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.122.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.123.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.124.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.125.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.126.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.experts.127.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.gate.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.shared_experts.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.shared_experts.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.q_proj.bias": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.k_proj.bias": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.self_attn.v_proj.bias": "model-00028-of-00041.safetensors", + "model.language_model.layers.31.mlp.gate.e_score_correction_bias": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.0.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.0.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.1.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.1.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.2.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.2.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.3.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.3.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.4.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.4.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.5.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.5.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.6.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.6.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.7.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.7.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.8.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.8.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.9.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.9.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.10.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.10.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.11.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.11.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.12.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.12.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.13.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.13.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.14.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.14.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.15.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.15.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.16.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.16.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.17.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.17.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.18.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.18.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.19.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.19.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.20.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.20.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.21.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.21.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.22.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.22.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.23.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.23.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.24.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.24.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.25.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.25.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.26.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.26.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.27.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.27.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.28.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.28.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.29.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.29.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.30.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.30.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.31.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.31.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.32.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.32.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.33.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.33.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.34.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.34.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.35.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.35.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.36.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.36.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.37.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.37.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.38.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.38.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.39.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.39.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.40.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.40.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.41.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.41.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.42.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.42.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.43.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.43.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.44.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.44.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.45.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.45.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.46.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.46.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.47.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.47.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.48.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.48.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.49.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.49.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.50.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.50.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.51.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.51.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.52.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.52.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.53.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.53.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.54.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.54.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.55.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.55.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.56.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.56.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.57.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.57.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.58.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.58.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.59.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.59.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.60.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.60.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.61.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.61.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.62.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.62.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.63.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.63.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.64.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.64.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.65.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.65.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.66.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.66.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.67.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.67.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.68.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.68.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.69.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.69.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.70.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.70.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.71.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.71.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.72.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.72.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.73.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.73.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.74.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.74.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.75.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.75.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.76.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.76.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.77.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.77.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.78.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.78.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.79.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.79.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.80.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.80.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.81.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.81.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.82.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.82.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.83.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.83.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.84.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.84.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.85.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.85.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.86.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.86.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.87.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.87.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.88.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.88.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.89.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.89.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.90.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.90.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.91.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.91.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.92.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.92.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.93.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.93.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.94.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.94.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.95.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.95.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.96.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.96.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.97.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.97.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.98.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.98.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.99.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.99.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.100.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.100.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.101.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.101.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.102.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.102.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.103.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.103.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.104.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.104.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.105.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.105.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.106.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.106.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.107.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.107.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.108.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.108.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.109.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.109.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.110.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.110.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.111.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.111.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.112.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.112.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.113.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.113.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.114.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.114.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.115.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.115.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.116.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.116.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.117.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.117.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.118.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.118.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.119.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.119.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.120.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.120.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.121.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.121.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.122.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.122.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.123.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.123.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.124.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.124.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.125.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.125.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.126.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.126.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.127.gate_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.127.up_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.0.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.1.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.2.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.3.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.4.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.5.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.6.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.7.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.8.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.9.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.10.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.11.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.12.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.13.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.14.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.15.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.16.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.17.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.18.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.19.down_proj.weight": "model-00028-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.20.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.21.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.22.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.23.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.24.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.25.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.26.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.27.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.28.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.29.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.30.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.31.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.32.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.33.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.34.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.35.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.36.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.37.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.38.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.39.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.40.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.41.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.42.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.43.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.44.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.45.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.46.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.47.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.48.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.49.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.50.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.51.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.52.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.53.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.54.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.55.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.56.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.57.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.58.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.59.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.60.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.61.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.62.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.63.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.64.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.65.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.66.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.67.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.68.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.69.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.70.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.71.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.72.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.73.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.74.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.75.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.76.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.77.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.78.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.79.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.80.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.81.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.82.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.83.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.84.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.85.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.86.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.87.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.88.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.89.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.90.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.91.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.92.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.93.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.94.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.95.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.96.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.97.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.98.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.99.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.100.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.101.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.102.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.103.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.104.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.105.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.106.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.107.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.108.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.109.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.110.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.111.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.112.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.113.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.114.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.115.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.116.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.117.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.118.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.119.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.120.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.121.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.122.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.123.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.124.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.125.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.126.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.experts.127.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.shared_experts.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.gate.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.shared_experts.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.q_proj.bias": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.k_proj.bias": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.self_attn.v_proj.bias": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.32.mlp.gate.e_score_correction_bias": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.0.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.0.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.1.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.1.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.2.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.2.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.3.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.3.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.4.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.4.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.5.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.5.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.6.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.6.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.7.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.7.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.8.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.8.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.9.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.9.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.10.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.10.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.11.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.11.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.12.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.12.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.13.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.13.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.14.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.14.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.15.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.15.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.16.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.16.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.17.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.17.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.18.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.18.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.19.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.19.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.20.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.20.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.21.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.21.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.22.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.22.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.23.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.23.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.24.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.24.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.25.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.25.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.26.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.26.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.27.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.27.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.28.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.28.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.29.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.29.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.30.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.30.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.31.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.31.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.32.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.32.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.33.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.33.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.34.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.34.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.35.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.35.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.36.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.36.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.37.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.37.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.38.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.38.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.39.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.39.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.40.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.40.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.41.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.41.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.42.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.42.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.43.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.43.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.44.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.44.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.45.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.45.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.46.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.46.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.47.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.47.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.48.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.48.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.49.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.49.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.50.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.50.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.51.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.51.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.52.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.52.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.53.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.53.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.54.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.54.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.55.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.55.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.56.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.56.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.57.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.57.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.58.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.58.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.59.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.59.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.60.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.60.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.61.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.61.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.62.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.62.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.63.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.63.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.64.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.64.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.65.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.65.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.66.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.66.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.67.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.67.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.68.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.68.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.69.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.69.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.70.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.70.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.71.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.71.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.72.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.72.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.73.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.73.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.74.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.74.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.75.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.75.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.76.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.76.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.77.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.77.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.78.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.78.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.79.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.79.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.80.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.80.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.81.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.81.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.82.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.82.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.83.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.83.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.84.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.84.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.85.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.85.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.86.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.86.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.87.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.87.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.88.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.88.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.89.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.89.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.90.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.90.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.91.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.91.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.92.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.92.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.93.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.93.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.94.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.94.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.95.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.95.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.96.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.96.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.97.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.97.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.98.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.98.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.99.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.99.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.100.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.100.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.101.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.101.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.102.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.102.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.103.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.103.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.104.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.104.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.105.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.105.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.106.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.106.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.107.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.107.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.108.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.108.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.109.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.109.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.110.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.110.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.111.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.111.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.112.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.112.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.113.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.113.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.114.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.114.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.115.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.115.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.116.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.116.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.117.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.117.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.118.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.118.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.119.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.119.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.120.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.120.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.121.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.121.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.122.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.122.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.123.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.123.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.124.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.124.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.125.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.125.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.126.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.126.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.127.gate_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.127.up_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.0.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.1.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.2.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.3.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.4.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.5.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.6.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.7.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.8.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.9.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.10.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.11.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.12.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.13.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.14.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.15.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.16.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.17.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.18.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.19.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.20.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.21.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.22.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.23.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.24.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.25.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.26.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.27.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.28.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.29.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.30.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.31.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.32.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.33.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.34.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.35.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.36.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.37.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.38.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.39.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.40.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.41.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.42.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.43.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.44.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.45.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.46.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.47.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.48.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.49.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.50.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.51.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.52.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.53.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.54.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.55.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.56.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.57.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.58.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.59.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.60.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.61.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.62.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.63.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.64.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.65.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.66.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.67.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.68.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.69.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.70.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.71.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.72.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.73.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.74.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.75.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.76.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.77.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.78.down_proj.weight": "model-00029-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.79.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.80.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.81.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.82.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.83.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.84.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.85.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.86.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.87.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.88.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.89.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.90.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.91.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.92.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.93.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.94.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.95.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.96.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.97.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.98.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.99.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.100.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.101.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.102.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.103.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.104.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.105.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.106.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.107.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.108.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.109.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.110.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.111.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.112.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.113.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.114.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.115.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.116.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.117.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.118.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.119.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.120.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.121.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.122.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.123.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.124.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.125.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.126.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.experts.127.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.shared_experts.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.gate.e_score_correction_bias": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.shared_experts.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.mlp.gate.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.q_proj.bias": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.k_proj.bias": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.v_proj.bias": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.0.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.0.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.1.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.1.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.2.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.2.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.3.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.3.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.4.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.4.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.5.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.5.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.6.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.6.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.7.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.7.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.8.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.8.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.9.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.9.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.10.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.10.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.11.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.11.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.12.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.12.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.13.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.13.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.14.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.14.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.15.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.15.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.16.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.16.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.17.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.17.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.18.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.18.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.19.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.19.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.20.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.20.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.21.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.21.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.22.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.22.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.23.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.23.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.24.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.24.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.25.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.25.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.26.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.26.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.27.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.27.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.28.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.28.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.29.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.29.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.30.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.30.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.31.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.31.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.32.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.32.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.33.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.33.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.34.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.34.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.35.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.35.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.36.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.36.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.37.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.37.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.38.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.38.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.39.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.39.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.40.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.40.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.41.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.41.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.42.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.42.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.43.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.43.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.44.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.44.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.45.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.45.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.46.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.46.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.47.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.47.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.48.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.48.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.49.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.49.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.50.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.50.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.51.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.51.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.52.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.52.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.53.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.53.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.54.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.54.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.55.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.55.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.56.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.56.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.57.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.57.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.58.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.58.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.59.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.59.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.60.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.60.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.61.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.61.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.62.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.62.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.63.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.63.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.64.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.64.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.65.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.65.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.66.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.66.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.67.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.67.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.68.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.68.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.69.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.69.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.70.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.70.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.71.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.71.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.72.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.72.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.73.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.73.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.74.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.74.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.75.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.75.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.76.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.76.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.77.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.77.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.78.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.78.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.79.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.79.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.80.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.80.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.81.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.81.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.82.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.82.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.83.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.83.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.84.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.84.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.85.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.85.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.86.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.86.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.87.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.87.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.88.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.88.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.89.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.89.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.90.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.90.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.91.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.91.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.92.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.92.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.93.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.93.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.94.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.94.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.95.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.95.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.96.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.96.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.97.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.97.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.98.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.98.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.99.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.99.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.100.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.100.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.101.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.101.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.102.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.102.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.103.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.103.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.104.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.104.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.105.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.105.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.106.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.106.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.107.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.107.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.108.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.108.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.109.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.109.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.110.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.110.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.111.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.111.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.112.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.112.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.113.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.113.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.114.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.114.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.115.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.115.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.116.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.116.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.117.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.117.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.118.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.118.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.119.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.119.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.120.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.120.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.121.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.121.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.122.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.122.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.123.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.123.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.124.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.124.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.125.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.125.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.126.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.126.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.127.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.127.up_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.0.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.1.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.2.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.3.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.4.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.5.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.6.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.7.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.8.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.9.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.10.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.11.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.12.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.13.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.14.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.15.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.16.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.17.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.18.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.19.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.20.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.21.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.22.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.23.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.24.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.25.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.26.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.27.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.28.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.29.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.30.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.31.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.32.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.33.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.34.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.35.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.36.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.37.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.38.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.39.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.40.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.41.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.42.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.43.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.44.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.45.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.46.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.47.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.48.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.49.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.50.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.51.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.52.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.53.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.54.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.55.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.56.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.57.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.58.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.59.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.60.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.61.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.62.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.63.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.64.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.65.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.66.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.67.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.68.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.69.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.70.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.71.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.72.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.73.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.74.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.75.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.76.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.77.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.78.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.79.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.80.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.81.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.82.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.83.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.84.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.85.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.86.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.87.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.88.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.89.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.90.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.91.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.92.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.93.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.94.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.95.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.96.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.97.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.98.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.99.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.100.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.101.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.102.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.103.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.104.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.105.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.106.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.107.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.108.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.109.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.110.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.111.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.112.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.113.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.114.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.115.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.116.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.117.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.118.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.119.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.120.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.121.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.122.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.123.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.124.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.125.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.126.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.experts.127.down_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00030-of-00041.safetensors", + "model.language_model.layers.34.mlp.shared_experts.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.mlp.shared_experts.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.mlp.gate.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.mlp.gate.e_score_correction_bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.self_attn.q_proj.bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.self_attn.k_proj.bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.self_attn.v_proj.bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.0.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.0.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.1.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.1.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.2.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.2.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.3.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.3.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.4.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.4.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.5.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.5.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.6.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.6.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.7.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.7.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.8.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.8.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.9.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.9.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.10.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.10.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.11.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.11.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.12.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.12.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.13.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.13.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.14.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.14.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.15.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.15.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.16.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.16.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.17.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.17.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.18.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.18.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.19.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.19.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.20.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.20.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.21.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.21.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.22.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.22.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.23.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.23.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.24.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.24.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.25.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.25.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.26.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.26.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.27.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.27.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.28.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.28.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.29.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.29.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.30.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.30.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.31.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.31.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.32.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.32.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.33.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.33.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.34.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.34.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.35.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.35.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.36.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.36.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.37.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.37.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.38.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.38.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.39.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.39.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.40.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.40.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.41.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.41.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.42.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.42.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.43.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.43.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.44.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.44.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.45.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.45.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.46.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.46.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.47.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.47.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.48.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.48.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.49.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.49.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.50.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.50.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.51.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.51.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.52.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.52.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.53.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.53.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.54.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.54.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.55.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.55.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.56.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.56.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.57.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.57.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.58.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.58.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.59.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.59.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.60.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.60.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.61.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.61.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.62.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.62.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.63.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.63.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.64.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.64.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.65.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.65.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.66.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.66.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.67.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.67.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.68.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.68.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.69.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.69.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.70.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.70.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.71.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.71.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.72.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.72.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.73.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.73.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.74.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.74.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.75.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.75.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.76.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.76.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.77.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.77.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.78.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.78.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.79.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.79.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.80.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.80.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.81.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.81.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.82.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.82.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.83.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.83.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.84.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.84.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.85.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.85.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.86.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.86.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.87.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.87.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.88.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.88.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.89.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.89.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.90.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.90.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.91.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.91.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.92.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.92.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.93.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.93.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.94.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.94.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.95.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.95.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.96.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.96.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.97.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.97.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.98.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.98.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.99.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.99.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.100.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.100.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.101.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.101.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.102.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.102.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.103.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.103.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.104.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.104.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.105.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.105.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.106.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.106.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.107.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.107.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.108.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.108.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.109.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.109.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.110.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.110.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.111.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.111.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.112.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.112.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.113.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.113.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.114.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.114.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.115.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.115.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.116.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.116.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.117.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.117.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.118.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.118.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.119.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.119.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.120.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.120.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.121.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.121.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.122.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.122.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.123.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.123.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.124.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.124.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.125.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.125.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.126.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.126.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.127.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.127.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.0.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.1.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.2.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.3.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.4.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.5.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.6.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.7.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.8.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.9.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.10.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.11.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.12.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.13.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.14.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.15.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.16.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.17.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.18.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.19.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.20.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.21.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.22.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.23.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.24.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.25.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.26.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.27.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.28.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.29.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.30.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.31.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.32.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.33.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.34.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.35.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.36.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.37.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.38.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.39.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.40.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.41.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.42.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.43.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.44.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.45.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.46.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.47.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.48.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.49.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.50.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.51.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.52.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.53.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.54.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.55.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.56.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.57.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.58.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.59.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.60.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.61.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.62.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.63.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.64.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.65.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.66.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.67.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.68.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.69.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.70.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.71.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.72.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.73.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.74.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.75.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.76.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.77.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.78.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.79.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.80.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.81.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.82.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.83.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.84.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.85.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.86.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.87.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.88.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.89.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.90.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.91.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.92.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.93.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.94.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.95.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.96.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.97.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.98.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.99.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.100.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.101.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.102.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.103.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.104.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.105.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.106.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.107.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.108.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.109.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.110.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.111.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.112.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.113.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.114.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.115.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.116.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.117.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.118.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.119.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.120.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.121.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.122.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.123.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.124.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.125.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.126.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.experts.127.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.shared_experts.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.shared_experts.down_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.gate.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.mlp.gate.e_score_correction_bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.q_proj.bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.k_proj.bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.35.self_attn.v_proj.bias": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.0.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.0.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.1.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.1.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.2.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.2.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.3.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.3.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.4.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.4.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.5.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.5.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.6.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.6.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.7.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.7.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.8.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.8.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.9.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.9.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.10.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.10.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.11.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.11.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.12.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.12.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.13.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.13.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.14.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.14.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.15.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.15.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.16.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.16.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.17.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.17.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.18.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.18.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.19.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.19.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.20.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.20.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.21.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.21.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.22.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.22.up_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.23.gate_proj.weight": "model-00031-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.23.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.24.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.24.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.25.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.25.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.26.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.26.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.27.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.27.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.28.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.28.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.29.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.29.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.30.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.30.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.31.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.31.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.32.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.32.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.33.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.33.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.34.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.34.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.35.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.35.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.36.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.36.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.37.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.37.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.38.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.38.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.39.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.39.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.40.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.40.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.41.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.41.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.42.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.42.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.43.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.43.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.44.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.44.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.45.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.45.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.46.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.46.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.47.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.47.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.48.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.48.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.49.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.49.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.50.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.50.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.51.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.51.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.52.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.52.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.53.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.53.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.54.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.54.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.55.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.55.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.56.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.56.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.57.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.57.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.58.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.58.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.59.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.59.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.60.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.60.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.61.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.61.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.62.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.62.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.63.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.63.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.64.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.64.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.65.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.65.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.66.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.66.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.67.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.67.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.68.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.68.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.69.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.69.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.70.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.70.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.71.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.71.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.72.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.72.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.73.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.73.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.74.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.74.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.75.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.75.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.76.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.76.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.77.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.77.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.78.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.78.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.79.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.79.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.80.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.80.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.81.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.81.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.82.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.82.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.83.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.83.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.84.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.84.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.85.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.85.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.86.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.86.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.87.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.87.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.88.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.88.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.89.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.89.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.90.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.90.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.91.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.91.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.92.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.92.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.93.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.93.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.94.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.94.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.95.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.95.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.96.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.96.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.97.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.97.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.98.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.98.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.99.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.99.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.100.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.100.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.101.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.101.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.102.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.102.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.103.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.103.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.104.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.104.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.105.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.105.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.106.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.106.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.107.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.107.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.108.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.108.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.109.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.109.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.110.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.110.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.111.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.111.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.112.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.112.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.113.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.113.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.114.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.114.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.115.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.115.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.116.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.116.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.117.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.117.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.118.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.118.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.119.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.119.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.120.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.120.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.121.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.121.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.122.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.122.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.123.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.123.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.124.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.124.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.125.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.125.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.126.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.126.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.127.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.127.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.0.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.1.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.2.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.3.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.4.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.5.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.6.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.7.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.8.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.9.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.10.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.11.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.12.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.13.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.14.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.15.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.16.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.17.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.18.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.19.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.20.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.21.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.22.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.23.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.24.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.25.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.26.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.27.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.28.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.29.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.30.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.31.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.32.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.33.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.34.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.35.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.36.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.37.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.38.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.39.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.40.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.41.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.42.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.43.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.44.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.45.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.46.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.47.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.48.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.49.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.50.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.51.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.52.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.53.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.54.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.55.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.56.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.57.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.58.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.59.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.60.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.61.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.62.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.63.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.64.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.65.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.66.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.67.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.68.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.69.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.70.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.71.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.72.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.73.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.74.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.75.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.76.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.77.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.78.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.79.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.80.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.81.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.82.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.83.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.84.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.85.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.86.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.87.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.88.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.89.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.90.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.91.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.92.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.93.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.94.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.95.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.96.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.97.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.98.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.99.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.100.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.101.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.102.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.103.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.104.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.105.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.106.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.107.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.108.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.109.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.110.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.111.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.112.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.113.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.114.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.115.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.116.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.117.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.118.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.119.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.120.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.121.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.122.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.123.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.124.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.125.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.126.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.experts.127.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.q_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.k_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.v_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.o_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.shared_experts.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.gate.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.shared_experts.down_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.q_proj.bias": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.k_proj.bias": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.self_attn.v_proj.bias": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.post_attention_layernorm.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.input_layernorm.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.36.mlp.gate.e_score_correction_bias": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.0.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.0.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.1.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.1.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.2.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.2.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.3.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.3.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.4.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.4.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.5.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.5.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.6.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.6.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.7.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.7.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.8.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.8.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.9.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.9.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.10.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.10.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.11.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.11.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.12.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.12.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.13.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.13.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.14.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.14.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.15.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.15.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.16.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.16.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.17.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.17.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.18.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.18.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.19.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.19.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.20.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.20.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.21.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.21.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.22.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.22.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.23.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.23.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.24.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.24.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.25.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.25.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.26.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.26.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.27.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.27.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.28.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.28.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.29.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.29.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.30.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.30.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.31.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.31.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.32.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.32.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.33.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.33.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.34.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.34.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.35.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.35.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.36.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.36.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.37.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.37.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.38.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.38.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.39.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.39.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.40.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.40.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.41.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.41.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.42.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.42.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.43.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.43.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.44.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.44.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.45.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.45.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.46.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.46.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.47.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.47.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.48.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.48.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.49.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.49.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.50.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.50.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.51.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.51.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.52.gate_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.52.up_proj.weight": "model-00032-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.53.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.53.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.54.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.54.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.55.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.55.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.56.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.56.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.57.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.57.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.58.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.58.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.59.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.59.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.60.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.60.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.61.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.61.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.62.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.62.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.63.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.63.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.64.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.64.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.65.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.65.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.66.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.66.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.67.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.67.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.68.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.68.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.69.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.69.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.70.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.70.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.71.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.71.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.72.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.72.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.73.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.73.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.74.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.74.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.75.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.75.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.76.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.76.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.77.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.77.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.78.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.78.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.79.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.79.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.80.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.80.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.81.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.81.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.82.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.82.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.83.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.83.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.84.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.84.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.85.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.85.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.86.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.86.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.87.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.87.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.88.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.88.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.89.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.89.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.90.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.90.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.91.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.91.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.92.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.92.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.93.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.93.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.94.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.94.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.95.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.95.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.96.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.96.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.97.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.97.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.98.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.98.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.99.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.99.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.100.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.100.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.101.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.101.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.102.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.102.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.103.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.103.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.104.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.104.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.105.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.105.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.106.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.106.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.107.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.107.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.108.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.108.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.109.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.109.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.110.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.110.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.111.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.111.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.112.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.112.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.113.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.113.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.114.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.114.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.115.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.115.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.116.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.116.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.117.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.117.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.118.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.118.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.119.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.119.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.120.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.120.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.121.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.121.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.122.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.122.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.123.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.123.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.124.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.124.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.125.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.125.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.126.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.126.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.127.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.127.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.0.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.1.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.2.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.3.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.4.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.5.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.6.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.7.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.8.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.9.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.10.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.11.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.12.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.13.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.14.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.15.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.16.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.17.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.18.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.19.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.20.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.21.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.22.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.23.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.24.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.25.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.26.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.27.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.28.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.29.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.30.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.31.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.32.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.33.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.34.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.35.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.36.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.37.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.38.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.39.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.40.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.41.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.42.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.43.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.44.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.45.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.46.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.47.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.48.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.49.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.50.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.51.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.52.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.53.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.54.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.55.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.56.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.57.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.58.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.59.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.60.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.61.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.62.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.63.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.64.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.65.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.66.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.67.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.68.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.69.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.70.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.71.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.72.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.73.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.74.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.75.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.76.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.77.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.78.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.79.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.80.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.81.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.82.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.83.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.84.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.85.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.86.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.87.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.88.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.89.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.90.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.91.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.92.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.93.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.94.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.95.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.96.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.97.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.98.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.99.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.100.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.101.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.102.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.103.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.104.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.105.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.106.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.107.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.108.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.109.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.110.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.111.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.112.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.113.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.114.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.115.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.116.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.117.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.118.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.119.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.120.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.121.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.122.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.123.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.124.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.125.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.126.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.experts.127.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.shared_experts.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.q_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.k_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.v_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.shared_experts.down_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.o_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.input_layernorm.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.gate.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.q_proj.bias": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.k_proj.bias": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.self_attn.v_proj.bias": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.post_attention_layernorm.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.37.mlp.gate.e_score_correction_bias": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.0.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.0.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.1.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.1.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.2.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.2.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.3.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.3.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.4.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.4.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.5.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.5.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.6.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.6.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.7.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.7.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.8.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.8.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.9.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.9.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.10.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.10.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.11.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.11.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.12.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.12.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.13.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.13.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.14.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.14.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.15.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.15.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.16.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.16.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.17.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.17.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.18.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.18.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.19.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.19.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.20.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.20.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.21.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.21.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.22.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.22.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.23.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.23.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.24.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.24.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.25.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.25.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.26.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.26.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.27.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.27.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.28.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.28.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.29.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.29.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.30.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.30.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.31.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.31.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.32.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.32.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.33.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.33.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.34.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.34.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.35.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.35.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.36.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.36.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.37.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.37.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.38.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.38.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.39.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.39.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.40.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.40.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.41.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.41.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.42.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.42.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.43.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.43.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.44.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.44.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.45.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.45.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.46.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.46.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.47.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.47.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.48.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.48.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.49.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.49.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.50.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.50.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.51.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.51.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.52.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.52.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.53.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.53.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.54.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.54.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.55.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.55.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.56.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.56.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.57.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.57.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.58.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.58.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.59.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.59.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.60.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.60.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.61.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.61.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.62.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.62.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.63.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.63.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.64.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.64.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.65.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.65.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.66.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.66.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.67.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.67.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.68.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.68.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.69.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.69.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.70.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.70.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.71.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.71.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.72.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.72.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.73.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.73.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.74.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.74.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.75.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.75.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.76.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.76.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.77.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.77.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.78.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.78.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.79.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.79.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.80.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.80.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.81.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.81.up_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.82.gate_proj.weight": "model-00033-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.82.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.83.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.83.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.84.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.84.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.85.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.85.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.86.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.86.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.87.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.87.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.88.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.88.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.89.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.89.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.90.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.90.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.91.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.91.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.92.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.92.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.93.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.93.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.94.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.94.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.95.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.95.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.96.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.96.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.97.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.97.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.98.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.98.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.99.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.99.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.100.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.100.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.101.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.101.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.102.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.102.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.103.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.103.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.104.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.104.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.105.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.105.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.106.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.106.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.107.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.107.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.108.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.108.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.109.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.109.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.110.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.110.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.111.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.111.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.112.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.112.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.113.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.113.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.114.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.114.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.115.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.115.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.116.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.116.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.117.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.117.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.118.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.118.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.119.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.119.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.120.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.120.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.121.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.121.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.122.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.122.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.123.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.123.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.124.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.124.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.125.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.125.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.126.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.126.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.127.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.127.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.0.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.1.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.2.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.3.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.4.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.5.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.6.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.7.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.8.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.9.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.10.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.11.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.12.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.13.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.14.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.15.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.16.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.17.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.18.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.19.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.20.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.21.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.22.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.23.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.24.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.25.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.26.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.27.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.28.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.29.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.30.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.31.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.32.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.33.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.34.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.35.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.36.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.37.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.38.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.39.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.40.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.41.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.42.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.43.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.44.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.45.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.46.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.47.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.48.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.49.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.50.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.51.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.52.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.53.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.54.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.55.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.56.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.57.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.58.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.59.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.60.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.61.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.62.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.63.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.64.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.65.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.66.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.67.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.68.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.69.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.70.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.71.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.72.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.73.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.74.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.75.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.76.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.77.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.78.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.79.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.80.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.81.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.82.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.83.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.84.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.85.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.86.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.87.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.88.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.89.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.90.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.91.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.92.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.93.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.94.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.95.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.96.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.97.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.98.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.99.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.100.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.101.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.102.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.103.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.104.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.105.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.106.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.107.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.108.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.109.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.110.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.111.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.112.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.113.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.114.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.115.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.116.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.117.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.118.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.119.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.120.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.121.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.122.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.123.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.124.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.125.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.126.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.experts.127.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.q_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.k_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.v_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.o_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.gate.e_score_correction_bias": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.shared_experts.down_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.post_attention_layernorm.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.gate.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.mlp.shared_experts.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.input_layernorm.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.q_proj.bias": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.k_proj.bias": "model-00034-of-00041.safetensors", + "model.language_model.layers.38.self_attn.v_proj.bias": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.0.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.0.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.1.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.1.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.2.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.2.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.3.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.3.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.4.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.4.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.5.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.5.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.6.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.6.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.7.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.7.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.8.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.8.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.9.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.9.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.10.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.10.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.11.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.11.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.12.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.12.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.13.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.13.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.14.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.14.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.15.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.15.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.16.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.16.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.17.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.17.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.18.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.18.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.19.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.19.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.20.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.20.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.21.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.21.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.22.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.22.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.23.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.23.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.24.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.24.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.25.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.25.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.26.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.26.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.27.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.27.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.28.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.28.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.29.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.29.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.30.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.30.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.31.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.31.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.32.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.32.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.33.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.33.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.34.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.34.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.35.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.35.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.36.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.36.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.37.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.37.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.38.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.38.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.39.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.39.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.40.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.40.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.41.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.41.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.42.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.42.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.43.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.43.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.44.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.44.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.45.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.45.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.46.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.46.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.47.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.47.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.48.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.48.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.49.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.49.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.50.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.50.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.51.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.51.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.52.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.52.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.53.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.53.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.54.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.54.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.55.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.55.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.56.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.56.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.57.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.57.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.58.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.58.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.59.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.59.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.60.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.60.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.61.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.61.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.62.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.62.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.63.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.63.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.64.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.64.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.65.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.65.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.66.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.66.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.67.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.67.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.68.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.68.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.69.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.69.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.70.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.70.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.71.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.71.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.72.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.72.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.73.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.73.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.74.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.74.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.75.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.75.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.76.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.76.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.77.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.77.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.78.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.78.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.79.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.79.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.80.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.80.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.81.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.81.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.82.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.82.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.83.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.83.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.84.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.84.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.85.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.85.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.86.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.86.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.87.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.87.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.88.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.88.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.89.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.89.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.90.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.90.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.91.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.91.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.92.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.92.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.93.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.93.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.94.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.94.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.95.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.95.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.96.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.96.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.97.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.97.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.98.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.98.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.99.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.99.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.100.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.100.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.101.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.101.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.102.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.102.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.103.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.103.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.104.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.104.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.105.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.105.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.106.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.106.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.107.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.107.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.108.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.108.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.109.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.109.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.110.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.110.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.111.gate_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.111.up_proj.weight": "model-00034-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.112.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.112.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.113.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.113.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.114.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.114.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.115.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.115.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.116.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.116.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.117.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.117.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.118.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.118.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.119.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.119.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.120.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.120.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.121.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.121.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.122.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.122.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.123.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.123.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.124.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.124.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.125.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.125.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.126.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.126.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.127.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.127.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.0.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.1.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.2.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.3.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.4.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.5.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.6.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.7.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.8.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.9.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.10.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.11.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.12.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.13.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.14.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.15.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.16.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.17.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.18.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.19.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.20.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.21.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.22.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.23.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.24.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.25.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.26.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.27.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.28.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.29.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.30.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.31.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.32.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.33.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.34.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.35.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.36.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.37.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.38.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.39.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.40.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.41.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.42.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.43.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.44.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.45.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.46.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.47.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.48.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.49.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.50.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.51.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.52.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.53.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.54.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.55.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.56.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.57.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.58.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.59.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.60.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.61.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.62.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.63.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.64.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.65.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.66.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.67.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.68.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.69.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.70.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.71.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.72.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.73.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.74.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.75.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.76.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.77.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.78.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.79.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.80.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.81.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.82.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.83.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.84.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.85.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.86.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.87.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.88.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.89.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.90.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.91.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.92.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.93.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.94.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.95.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.96.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.97.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.98.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.99.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.100.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.101.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.102.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.103.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.104.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.105.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.106.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.107.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.108.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.109.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.110.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.111.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.112.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.113.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.114.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.115.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.116.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.117.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.118.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.119.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.120.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.121.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.122.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.123.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.124.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.125.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.126.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.experts.127.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.q_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.v_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.o_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.shared_experts.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.shared_experts.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.q_proj.bias": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.k_proj.bias": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.self_attn.v_proj.bias": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.gate.e_score_correction_bias": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.mlp.gate.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.39.input_layernorm.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.0.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.0.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.1.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.1.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.2.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.2.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.3.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.3.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.4.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.4.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.5.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.5.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.6.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.6.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.7.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.7.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.8.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.8.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.9.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.9.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.10.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.10.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.11.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.11.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.12.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.12.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.13.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.13.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.14.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.14.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.15.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.15.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.16.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.16.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.17.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.17.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.18.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.18.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.19.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.19.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.20.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.20.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.21.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.21.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.22.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.22.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.23.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.23.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.24.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.24.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.25.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.25.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.26.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.26.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.27.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.27.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.28.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.28.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.29.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.29.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.30.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.30.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.31.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.31.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.32.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.32.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.33.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.33.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.34.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.34.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.35.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.35.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.36.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.36.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.37.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.37.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.38.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.38.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.39.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.39.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.40.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.40.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.41.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.41.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.42.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.42.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.43.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.43.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.44.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.44.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.45.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.45.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.46.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.46.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.47.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.47.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.48.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.48.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.49.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.49.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.50.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.50.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.51.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.51.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.52.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.52.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.53.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.53.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.54.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.54.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.55.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.55.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.56.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.56.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.57.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.57.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.58.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.58.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.59.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.59.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.60.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.60.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.61.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.61.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.62.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.62.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.63.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.63.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.64.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.64.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.65.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.65.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.66.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.66.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.67.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.67.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.68.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.68.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.69.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.69.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.70.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.70.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.71.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.71.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.72.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.72.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.73.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.73.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.74.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.74.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.75.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.75.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.76.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.76.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.77.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.77.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.78.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.78.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.79.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.79.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.80.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.80.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.81.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.81.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.82.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.82.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.83.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.83.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.84.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.84.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.85.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.85.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.86.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.86.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.87.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.87.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.88.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.88.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.89.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.89.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.90.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.90.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.91.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.91.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.92.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.92.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.93.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.93.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.94.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.94.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.95.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.95.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.96.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.96.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.97.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.97.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.98.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.98.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.99.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.99.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.100.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.100.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.101.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.101.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.102.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.102.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.103.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.103.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.104.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.104.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.105.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.105.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.106.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.106.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.107.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.107.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.108.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.108.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.109.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.109.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.110.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.110.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.111.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.111.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.112.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.112.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.113.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.113.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.114.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.114.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.115.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.115.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.116.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.116.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.117.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.117.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.118.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.118.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.119.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.119.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.120.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.120.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.121.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.121.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.122.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.122.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.123.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.123.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.124.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.124.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.125.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.125.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.126.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.126.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.127.gate_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.127.up_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.0.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.1.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.2.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.3.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.4.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.5.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.6.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.7.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.8.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.9.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.10.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.11.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.12.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.13.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.14.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.15.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.16.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.17.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.18.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.19.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.20.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.21.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.22.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.23.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.24.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.25.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.26.down_proj.weight": "model-00035-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.27.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.28.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.29.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.30.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.31.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.32.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.33.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.34.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.35.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.36.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.37.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.38.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.39.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.40.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.41.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.42.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.43.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.44.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.45.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.46.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.47.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.48.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.49.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.50.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.51.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.52.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.53.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.54.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.55.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.56.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.57.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.58.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.59.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.60.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.61.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.62.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.63.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.64.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.65.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.66.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.67.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.68.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.69.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.70.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.71.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.72.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.73.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.74.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.75.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.76.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.77.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.78.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.79.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.80.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.81.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.82.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.83.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.84.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.85.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.86.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.87.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.88.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.89.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.90.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.91.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.92.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.93.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.94.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.95.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.96.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.97.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.98.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.99.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.100.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.101.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.102.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.103.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.104.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.105.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.106.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.107.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.108.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.109.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.110.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.111.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.112.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.113.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.114.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.115.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.116.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.117.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.118.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.119.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.120.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.121.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.122.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.123.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.124.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.125.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.126.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.experts.127.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.gate.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.q_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.k_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.v_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.shared_experts.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.post_attention_layernorm.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.shared_experts.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.input_layernorm.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.mlp.gate.e_score_correction_bias": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.q_proj.bias": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.k_proj.bias": "model-00036-of-00041.safetensors", + "model.language_model.layers.40.self_attn.v_proj.bias": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.0.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.0.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.1.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.1.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.2.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.2.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.3.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.3.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.4.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.4.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.5.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.5.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.6.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.6.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.7.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.7.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.8.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.8.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.9.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.9.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.10.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.10.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.11.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.11.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.12.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.12.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.13.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.13.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.14.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.14.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.15.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.15.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.16.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.16.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.17.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.17.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.18.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.18.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.19.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.19.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.20.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.20.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.21.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.21.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.22.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.22.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.23.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.23.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.24.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.24.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.25.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.25.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.26.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.26.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.27.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.27.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.28.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.28.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.29.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.29.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.30.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.30.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.31.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.31.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.32.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.32.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.33.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.33.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.34.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.34.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.35.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.35.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.36.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.36.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.37.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.37.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.38.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.38.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.39.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.39.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.40.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.40.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.41.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.41.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.42.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.42.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.43.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.43.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.44.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.44.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.45.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.45.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.46.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.46.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.47.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.47.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.48.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.48.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.49.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.49.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.50.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.50.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.51.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.51.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.52.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.52.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.53.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.53.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.54.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.54.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.55.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.55.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.56.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.56.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.57.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.57.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.58.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.58.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.59.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.59.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.60.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.60.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.61.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.61.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.62.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.62.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.63.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.63.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.64.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.64.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.65.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.65.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.66.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.66.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.67.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.67.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.68.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.68.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.69.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.69.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.70.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.70.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.71.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.71.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.72.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.72.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.73.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.73.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.74.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.74.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.75.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.75.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.76.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.76.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.77.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.77.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.78.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.78.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.79.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.79.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.80.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.80.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.81.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.81.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.82.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.82.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.83.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.83.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.84.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.84.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.85.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.85.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.86.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.86.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.87.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.87.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.88.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.88.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.89.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.89.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.90.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.90.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.91.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.91.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.92.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.92.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.93.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.93.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.94.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.94.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.95.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.95.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.96.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.96.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.97.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.97.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.98.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.98.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.99.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.99.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.100.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.100.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.101.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.101.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.102.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.102.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.103.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.103.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.104.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.104.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.105.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.105.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.106.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.106.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.107.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.107.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.108.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.108.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.109.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.109.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.110.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.110.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.111.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.111.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.112.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.112.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.113.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.113.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.114.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.114.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.115.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.115.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.116.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.116.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.117.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.117.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.118.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.118.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.119.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.119.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.120.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.120.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.121.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.121.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.122.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.122.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.123.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.123.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.124.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.124.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.125.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.125.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.126.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.126.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.127.gate_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.127.up_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.0.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.1.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.2.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.3.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.4.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.5.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.6.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.7.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.8.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.9.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.10.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.11.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.12.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.13.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.14.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.15.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.16.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.17.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.18.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.19.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.20.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.21.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.22.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.23.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.24.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.25.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.26.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.27.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.28.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.29.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.30.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.31.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.32.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.33.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.34.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.35.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.36.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.37.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.38.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.39.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.40.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.41.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.42.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.43.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.44.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.45.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.46.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.47.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.48.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.49.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.50.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.51.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.52.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.53.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.54.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.55.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.56.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.57.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.58.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.59.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.60.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.61.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.62.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.63.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.64.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.65.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.66.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.67.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.68.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.69.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.70.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.71.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.72.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.73.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.74.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.75.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.76.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.77.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.78.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.79.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.80.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.81.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.82.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.83.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.84.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.85.down_proj.weight": "model-00036-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.86.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.87.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.88.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.89.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.90.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.91.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.92.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.93.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.94.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.95.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.96.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.97.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.98.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.99.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.100.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.101.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.102.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.103.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.104.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.105.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.106.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.107.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.108.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.109.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.110.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.111.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.112.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.113.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.114.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.115.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.116.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.117.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.118.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.119.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.120.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.121.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.122.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.123.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.124.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.125.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.126.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.experts.127.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.gate.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.shared_experts.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.input_layernorm.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.k_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.v_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.q_proj.bias": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.k_proj.bias": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.self_attn.v_proj.bias": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.shared_experts.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.post_attention_layernorm.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.41.mlp.gate.e_score_correction_bias": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.0.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.0.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.1.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.1.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.2.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.2.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.3.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.3.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.4.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.4.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.5.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.5.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.6.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.6.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.7.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.7.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.8.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.8.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.9.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.9.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.10.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.10.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.11.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.11.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.12.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.12.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.13.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.13.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.14.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.14.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.15.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.15.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.16.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.16.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.17.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.17.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.18.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.18.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.19.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.19.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.20.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.20.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.21.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.21.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.22.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.22.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.23.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.23.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.24.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.24.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.25.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.25.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.26.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.26.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.27.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.27.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.28.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.28.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.29.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.29.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.30.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.30.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.31.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.31.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.32.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.32.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.33.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.33.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.34.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.34.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.35.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.35.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.36.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.36.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.37.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.37.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.38.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.38.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.39.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.39.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.40.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.40.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.41.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.41.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.42.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.42.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.43.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.43.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.44.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.44.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.45.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.45.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.46.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.46.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.47.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.47.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.48.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.48.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.49.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.49.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.50.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.50.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.51.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.51.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.52.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.52.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.53.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.53.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.54.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.54.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.55.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.55.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.56.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.56.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.57.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.57.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.58.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.58.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.59.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.59.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.60.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.60.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.61.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.61.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.62.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.62.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.63.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.63.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.64.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.64.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.65.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.65.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.66.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.66.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.67.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.67.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.68.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.68.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.69.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.69.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.70.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.70.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.71.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.71.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.72.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.72.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.73.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.73.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.74.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.74.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.75.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.75.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.76.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.76.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.77.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.77.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.78.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.78.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.79.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.79.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.80.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.80.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.81.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.81.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.82.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.82.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.83.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.83.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.84.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.84.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.85.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.85.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.86.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.86.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.87.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.87.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.88.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.88.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.89.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.89.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.90.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.90.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.91.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.91.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.92.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.92.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.93.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.93.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.94.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.94.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.95.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.95.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.96.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.96.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.97.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.97.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.98.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.98.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.99.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.99.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.100.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.100.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.101.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.101.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.102.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.102.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.103.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.103.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.104.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.104.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.105.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.105.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.106.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.106.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.107.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.107.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.108.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.108.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.109.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.109.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.110.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.110.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.111.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.111.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.112.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.112.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.113.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.113.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.114.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.114.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.115.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.115.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.116.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.116.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.117.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.117.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.118.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.118.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.119.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.119.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.120.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.120.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.121.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.121.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.122.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.122.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.123.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.123.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.124.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.124.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.125.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.125.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.126.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.126.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.127.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.127.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.0.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.1.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.2.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.3.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.4.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.5.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.6.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.7.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.8.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.9.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.10.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.11.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.12.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.13.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.14.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.15.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.16.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.17.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.18.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.19.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.20.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.21.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.22.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.23.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.24.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.25.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.26.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.27.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.28.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.29.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.30.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.31.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.32.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.33.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.34.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.35.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.36.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.37.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.38.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.39.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.40.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.41.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.42.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.43.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.44.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.45.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.46.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.47.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.48.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.49.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.50.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.51.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.52.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.53.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.54.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.55.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.56.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.57.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.58.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.59.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.60.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.61.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.62.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.63.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.64.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.65.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.66.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.67.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.68.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.69.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.70.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.71.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.72.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.73.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.74.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.75.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.76.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.77.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.78.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.79.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.80.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.81.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.82.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.83.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.84.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.85.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.86.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.87.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.88.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.89.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.90.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.91.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.92.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.93.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.94.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.95.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.96.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.97.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.98.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.99.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.100.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.101.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.102.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.103.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.104.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.105.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.106.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.107.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.108.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.109.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.110.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.111.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.112.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.113.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.114.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.115.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.116.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.117.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.118.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.119.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.120.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.121.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.122.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.123.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.124.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.125.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.126.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.experts.127.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.gate.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.shared_experts.up_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.gate.e_score_correction_bias": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.mlp.shared_experts.down_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.self_attn.k_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.self_attn.v_proj.weight": "model-00037-of-00041.safetensors", + "model.language_model.layers.42.self_attn.o_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.42.post_attention_layernorm.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.42.input_layernorm.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.42.self_attn.q_proj.bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.42.self_attn.k_proj.bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.42.self_attn.v_proj.bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.0.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.0.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.1.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.1.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.2.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.2.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.3.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.3.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.4.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.4.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.5.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.5.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.6.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.6.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.7.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.7.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.8.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.8.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.9.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.9.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.10.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.10.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.11.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.11.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.12.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.12.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.13.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.13.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.14.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.14.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.15.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.15.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.16.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.16.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.17.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.17.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.18.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.18.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.19.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.19.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.20.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.20.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.21.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.21.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.22.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.22.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.23.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.23.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.24.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.24.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.25.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.25.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.26.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.26.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.27.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.27.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.28.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.28.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.29.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.29.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.30.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.30.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.31.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.31.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.32.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.32.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.33.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.33.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.34.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.34.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.35.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.35.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.36.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.36.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.37.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.37.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.38.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.38.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.39.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.39.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.40.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.40.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.41.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.41.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.42.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.42.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.43.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.43.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.44.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.44.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.45.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.45.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.46.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.46.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.47.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.47.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.48.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.48.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.49.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.49.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.50.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.50.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.51.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.51.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.52.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.52.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.53.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.53.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.54.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.54.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.55.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.55.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.56.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.56.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.57.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.57.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.58.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.58.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.59.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.59.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.60.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.60.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.61.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.61.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.62.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.62.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.63.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.63.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.64.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.64.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.65.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.65.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.66.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.66.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.67.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.67.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.68.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.68.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.69.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.69.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.70.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.70.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.71.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.71.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.72.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.72.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.73.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.73.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.74.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.74.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.75.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.75.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.76.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.76.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.77.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.77.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.78.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.78.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.79.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.79.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.80.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.80.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.81.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.81.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.82.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.82.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.83.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.83.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.84.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.84.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.85.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.85.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.86.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.86.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.87.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.87.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.88.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.88.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.89.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.89.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.90.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.90.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.91.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.91.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.92.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.92.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.93.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.93.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.94.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.94.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.95.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.95.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.96.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.96.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.97.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.97.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.98.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.98.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.99.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.99.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.100.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.100.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.101.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.101.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.102.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.102.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.103.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.103.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.104.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.104.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.105.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.105.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.106.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.106.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.107.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.107.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.108.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.108.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.109.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.109.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.110.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.110.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.111.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.111.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.112.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.112.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.113.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.113.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.114.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.114.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.115.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.115.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.116.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.116.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.117.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.117.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.118.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.118.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.119.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.119.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.120.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.120.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.121.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.121.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.122.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.122.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.123.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.123.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.124.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.124.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.125.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.125.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.126.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.126.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.127.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.127.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.0.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.1.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.2.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.3.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.4.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.5.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.6.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.7.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.8.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.9.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.10.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.11.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.12.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.13.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.14.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.15.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.16.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.17.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.18.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.19.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.20.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.21.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.22.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.23.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.24.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.25.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.26.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.27.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.28.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.29.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.30.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.31.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.32.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.33.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.34.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.35.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.36.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.37.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.38.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.39.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.40.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.41.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.42.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.43.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.44.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.45.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.46.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.47.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.48.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.49.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.50.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.51.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.52.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.53.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.54.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.55.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.56.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.57.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.58.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.59.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.60.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.61.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.62.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.63.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.64.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.65.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.66.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.67.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.68.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.69.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.70.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.71.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.72.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.73.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.74.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.75.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.76.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.77.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.78.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.79.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.80.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.81.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.82.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.83.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.84.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.85.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.86.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.87.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.88.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.89.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.90.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.91.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.92.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.93.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.94.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.95.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.96.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.97.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.98.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.99.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.100.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.101.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.102.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.103.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.104.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.105.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.106.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.107.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.108.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.109.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.110.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.111.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.112.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.113.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.114.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.115.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.116.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.117.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.118.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.119.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.120.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.121.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.122.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.123.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.124.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.125.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.126.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.experts.127.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.shared_experts.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.k_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.gate.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.shared_experts.down_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.o_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.mlp.gate.e_score_correction_bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.post_attention_layernorm.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.input_layernorm.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.q_proj.bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.k_proj.bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.43.self_attn.v_proj.bias": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.0.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.0.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.1.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.1.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.2.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.2.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.3.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.3.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.4.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.4.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.5.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.5.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.6.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.6.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.7.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.7.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.8.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.8.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.9.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.9.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.10.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.10.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.11.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.11.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.12.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.12.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.13.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.13.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.14.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.14.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.15.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.15.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.16.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.16.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.17.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.17.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.18.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.18.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.19.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.19.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.20.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.20.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.21.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.21.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.22.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.22.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.23.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.23.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.24.gate_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.24.up_proj.weight": "model-00038-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.25.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.25.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.26.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.26.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.27.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.27.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.28.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.28.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.29.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.29.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.30.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.30.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.31.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.31.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.32.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.32.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.33.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.33.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.34.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.34.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.35.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.35.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.36.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.36.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.37.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.37.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.38.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.38.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.39.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.39.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.40.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.40.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.41.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.41.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.42.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.42.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.43.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.43.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.44.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.44.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.45.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.45.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.46.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.46.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.47.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.47.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.48.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.48.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.49.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.49.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.50.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.50.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.51.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.51.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.52.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.52.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.53.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.53.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.54.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.54.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.55.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.55.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.56.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.56.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.57.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.57.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.58.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.58.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.59.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.59.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.60.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.60.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.61.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.61.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.62.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.62.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.63.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.63.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.64.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.64.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.65.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.65.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.66.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.66.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.67.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.67.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.68.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.68.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.69.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.69.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.70.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.70.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.71.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.71.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.72.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.72.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.73.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.73.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.74.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.74.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.75.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.75.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.76.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.76.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.77.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.77.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.78.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.78.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.79.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.79.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.80.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.80.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.81.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.81.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.82.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.82.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.83.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.83.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.84.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.84.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.85.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.85.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.86.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.86.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.87.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.87.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.88.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.88.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.89.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.89.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.90.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.90.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.91.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.91.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.92.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.92.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.93.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.93.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.94.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.94.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.95.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.95.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.96.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.96.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.97.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.97.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.98.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.98.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.99.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.99.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.100.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.100.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.101.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.101.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.102.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.102.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.103.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.103.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.104.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.104.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.105.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.105.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.106.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.106.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.107.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.107.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.108.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.108.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.109.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.109.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.110.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.110.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.111.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.111.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.112.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.112.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.113.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.113.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.114.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.114.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.115.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.115.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.116.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.116.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.117.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.117.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.118.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.118.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.119.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.119.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.120.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.120.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.121.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.121.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.122.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.122.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.123.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.123.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.124.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.124.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.125.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.125.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.126.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.126.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.127.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.127.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.0.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.1.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.2.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.3.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.4.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.5.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.6.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.7.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.8.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.9.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.10.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.11.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.12.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.13.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.14.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.15.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.16.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.17.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.18.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.19.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.20.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.21.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.22.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.23.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.24.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.25.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.26.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.27.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.28.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.29.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.30.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.31.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.32.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.33.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.34.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.35.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.36.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.37.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.38.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.39.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.40.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.41.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.42.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.43.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.44.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.45.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.46.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.47.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.48.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.49.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.50.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.51.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.52.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.53.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.54.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.55.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.56.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.57.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.58.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.59.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.60.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.61.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.62.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.63.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.64.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.65.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.66.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.67.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.68.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.69.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.70.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.71.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.72.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.73.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.74.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.75.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.76.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.77.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.78.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.79.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.80.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.81.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.82.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.83.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.84.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.85.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.86.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.87.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.88.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.89.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.90.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.91.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.92.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.93.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.94.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.95.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.96.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.97.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.98.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.99.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.100.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.101.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.102.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.103.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.104.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.105.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.106.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.107.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.108.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.109.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.110.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.111.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.112.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.113.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.114.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.115.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.116.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.117.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.118.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.119.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.120.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.121.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.122.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.123.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.124.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.125.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.126.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.experts.127.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.gate.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.shared_experts.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.shared_experts.down_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.input_layernorm.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.q_proj.bias": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.k_proj.bias": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.self_attn.v_proj.bias": "model-00039-of-00041.safetensors", + "model.language_model.layers.44.mlp.gate.e_score_correction_bias": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.0.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.0.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.1.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.1.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.2.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.2.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.3.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.3.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.4.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.4.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.5.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.5.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.6.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.6.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.7.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.7.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.8.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.8.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.9.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.9.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.10.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.10.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.11.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.11.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.12.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.12.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.13.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.13.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.14.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.14.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.15.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.15.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.16.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.16.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.17.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.17.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.18.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.18.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.19.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.19.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.20.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.20.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.21.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.21.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.22.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.22.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.23.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.23.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.24.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.24.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.25.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.25.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.26.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.26.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.27.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.27.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.28.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.28.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.29.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.29.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.30.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.30.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.31.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.31.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.32.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.32.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.33.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.33.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.34.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.34.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.35.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.35.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.36.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.36.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.37.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.37.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.38.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.38.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.39.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.39.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.40.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.40.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.41.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.41.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.42.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.42.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.43.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.43.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.44.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.44.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.45.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.45.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.46.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.46.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.47.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.47.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.48.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.48.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.49.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.49.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.50.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.50.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.51.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.51.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.52.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.52.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.53.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.53.up_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.54.gate_proj.weight": "model-00039-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.54.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.55.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.55.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.56.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.56.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.57.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.57.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.58.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.58.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.59.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.59.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.60.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.60.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.61.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.61.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.62.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.62.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.63.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.63.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.64.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.64.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.65.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.65.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.66.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.66.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.67.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.67.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.68.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.68.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.69.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.69.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.70.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.70.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.71.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.71.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.72.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.72.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.73.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.73.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.74.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.74.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.75.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.75.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.76.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.76.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.77.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.77.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.78.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.78.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.79.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.79.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.80.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.80.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.81.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.81.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.82.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.82.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.83.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.83.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.84.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.84.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.85.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.85.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.86.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.86.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.87.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.87.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.88.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.88.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.89.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.89.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.90.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.90.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.91.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.91.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.92.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.92.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.93.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.93.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.94.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.94.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.95.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.95.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.96.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.96.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.97.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.97.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.98.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.98.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.99.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.99.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.100.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.100.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.101.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.101.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.102.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.102.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.103.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.103.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.104.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.104.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.105.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.105.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.106.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.106.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.107.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.107.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.108.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.108.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.109.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.109.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.110.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.110.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.111.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.111.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.112.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.112.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.113.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.113.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.114.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.114.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.115.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.115.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.116.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.116.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.117.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.117.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.118.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.118.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.119.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.119.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.120.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.120.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.121.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.121.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.122.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.122.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.123.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.123.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.124.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.124.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.125.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.125.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.126.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.126.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.127.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.127.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.0.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.1.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.2.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.3.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.4.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.5.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.6.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.7.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.8.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.9.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.10.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.11.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.12.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.13.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.14.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.15.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.16.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.17.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.18.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.19.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.20.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.21.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.22.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.23.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.24.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.25.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.26.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.27.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.28.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.29.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.30.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.31.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.32.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.33.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.34.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.35.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.36.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.37.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.38.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.39.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.40.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.41.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.42.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.43.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.44.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.45.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.46.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.47.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.48.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.49.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.50.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.51.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.52.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.53.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.54.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.55.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.56.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.57.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.58.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.59.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.60.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.61.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.62.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.63.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.64.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.65.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.66.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.67.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.68.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.69.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.70.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.71.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.72.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.73.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.74.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.75.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.76.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.77.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.78.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.79.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.80.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.81.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.82.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.83.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.84.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.85.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.86.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.87.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.88.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.89.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.90.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.91.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.92.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.93.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.94.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.95.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.96.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.97.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.98.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.99.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.100.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.101.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.102.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.103.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.104.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.105.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.106.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.107.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.108.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.109.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.110.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.111.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.112.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.113.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.114.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.115.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.116.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.117.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.118.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.119.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.120.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.121.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.122.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.123.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.124.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.125.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.126.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.experts.127.down_proj.weight": "model-00040-of-00041.safetensors", + "lm_head.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.q_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.k_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.v_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.gate.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.o_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.shared_experts.up_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.shared_experts.down_proj.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.post_attention_layernorm.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.input_layernorm.weight": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.q_proj.bias": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.k_proj.bias": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.self_attn.v_proj.bias": "model-00040-of-00041.safetensors", + "model.language_model.layers.45.mlp.gate.e_score_correction_bias": "model-00040-of-00041.safetensors", + "model.language_model.norm.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.0.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.0.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.1.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.1.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.2.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.2.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.3.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.3.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.4.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.4.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.5.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.5.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.6.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.6.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.7.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.7.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.8.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.8.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.9.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.9.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.10.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.10.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.11.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.11.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.12.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.12.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.13.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.13.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.14.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.14.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.15.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.15.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.16.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.16.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.17.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.17.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.18.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.18.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.19.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.19.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.20.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.20.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.21.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.21.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.22.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.22.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.23.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.23.mlp.up_proj.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00040-of-00041.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.0.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.1.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.2.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.3.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.4.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.5.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.6.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.7.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.8.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.9.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.10.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.11.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.12.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.13.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.14.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.15.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.16.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.17.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.18.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.19.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.20.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.21.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.22.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.23.mlp.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.patch_embed.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00041-of-00041.safetensors", + "model.visual.merger.post_projection_norm.bias": "model-00041-of-00041.safetensors", + "model.visual.embeddings.position_embedding.weight": "model-00041-of-00041.safetensors", + "model.visual.merger.gate_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.merger.up_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.merger.down_proj.weight": "model-00041-of-00041.safetensors", + "model.visual.downsample.weight": "model-00041-of-00041.safetensors", + "model.visual.merger.post_projection_norm.weight": "model-00041-of-00041.safetensors", + "model.visual.post_conv_layernorm.weight": "model-00041-of-00041.safetensors", + "model.visual.patch_embed.proj.bias": "model-00041-of-00041.safetensors", + "model.visual.merger.proj.weight": "model-00041-of-00041.safetensors", + "model.visual.post_layernorm.weight": "model-00041-of-00041.safetensors", + "model.visual.downsample.bias": "model-00041-of-00041.safetensors" + } +} \ No newline at end of file diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..308553695af766b3e3d05e68279d2c690e73273e --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,11 @@ +{ + "size": {"shortest_edge": 12544, "longest_edge": 9633792}, + "do_rescale": true, + "patch_size": 14, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [0.48145466, 0.4578275, 0.40821073], + "image_std": [0.26862954, 0.26130258, 0.27577711], + "image_processor_type": "Glm46VImageProcessor", + "processor_class": "Glm46VProcessor" +} diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..5498a3d751a0295aa628ae6cf4dbb544c4e9e4fc --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +torch +safetensors +tqdm \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..43a71efad1ab3f7e4d66d1e48e7cc44f68f21f3a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd +size 19970699 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a06c65d8bd9907f0088f1c2971aa363642f761c3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,327 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|image|>", + "<|video|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizer" +} diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..52f4d0d1dfbc7a5ed58f2bfae105d9436cd9037a --- /dev/null +++ b/video_preprocessor_config.json @@ -0,0 +1,11 @@ +{ + "size": {"shortest_edge": 12544, "longest_edge": 47040000}, + "do_rescale": true, + "patch_size": 14, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [0.48145466, 0.4578275, 0.40821073], + "image_std": [0.26862954, 0.26130258, 0.27577711], + "video_processor_type": "Glm46VVideoProcessor", + "processor_class": "Glm46VProcessor" +}