Upload folder using huggingface_hub

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model:
+- AlSamCur123/Mistral3InstructContinuedFine
+- AlSamCur123/Mistral3InstructLogicContinuedFine
+- AlSamCur123/mistral-7b2ContinuedFine
+- AlSamCur123/Mistral3InstructLogicContinuedFine
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- AlSamCur123/Mistral3InstructContinuedFine
+- AlSamCur123/Mistral3InstructLogicContinuedFine
+- AlSamCur123/mistral-7b2ContinuedFine
+---
+
+# mistral3instruct-4x7MOE
+
+mistral3instruct-4x7MOE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [AlSamCur123/Mistral3InstructContinuedFine](https://huggingface.co/AlSamCur123/Mistral3InstructContinuedFine)
+* [AlSamCur123/Mistral3InstructLogicContinuedFine](https://huggingface.co/AlSamCur123/Mistral3InstructLogicContinuedFine)
+* [AlSamCur123/mistral-7b2ContinuedFine](https://huggingface.co/AlSamCur123/mistral-7b2ContinuedFine)
+* [AlSamCur123/Mistral3InstructLogicContinuedFine](https://huggingface.co/AlSamCur123/Mistral3InstructLogicContinuedFine)
+
+## 🧩 Configuration
+
+```yaml
+base_model: AlSamCur123/Mistral3InstructContinuedFine
+experts:
+  - source_model: AlSamCur123/Mistral3InstructContinuedFine
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "I want"
+  - source_model: AlSamCur123/Mistral3InstructLogicContinuedFine
+    positive_prompts:
+    - "code"
+    - "python"
+    - "javascript"
+    - "programming"
+    - "algorithm"
+  - source_model: AlSamCur123/mistral-7b2ContinuedFine
+    positive_prompts:
+    - "storywriting"
+    - "write"
+    - "scene"
+    - "story"
+    - "character"
+  - source_model: AlSamCur123/Mistral3InstructLogicContinuedFine
+    positive_prompts:
+    - "reason"
+    - "math"
+    - "mathematics"
+    - "solve"
+    - "count"
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "AlSamCur123/mistral3instruct-4x7MOE"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "AlSamCur123/Mistral3InstructContinuedFine",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 770,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "unsloth_version": "2025.2.5",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_moe_config.yml

@@ -0,0 +1,32 @@
+
+base_model: AlSamCur123/Mistral3InstructContinuedFine
+experts:
+  - source_model: AlSamCur123/Mistral3InstructContinuedFine
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "I want"
+  - source_model: AlSamCur123/Mistral3InstructLogicContinuedFine
+    positive_prompts:
+    - "code"
+    - "python"
+    - "javascript"
+    - "programming"
+    - "algorithm"
+  - source_model: AlSamCur123/mistral-7b2ContinuedFine
+    positive_prompts:
+    - "storywriting"
+    - "write"
+    - "scene"
+    - "story"
+    - "character"
+  - source_model: AlSamCur123/Mistral3InstructLogicContinuedFine
+    positive_prompts:
+    - "reason"
+    - "math"
+    - "mathematics"
+    - "solve"
+    - "count"
+

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7032e44ac508ac2d74ca6a54240c3c98e2a28bac72373ecda1ec79f3016c4d0f
+size 4949351960

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac550b64c54eed33e374ad5ddd7c03d5a56a82c2601e66b9e4e1e2450ccb0730
+size 4949335168

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e175bd1c46e3ec79a32d66fa41845f1e9de08f9902b4812cf0c1486d7cb7837
+size 4949335168

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79fe3de2a0b61a282d72b87d663c8993409bef01749f221f34475b237df5c00
+size 4915797744

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2023a10025bc9640f8b6f2c7084118f6e20e0f26cc6a8cc0117da57bbf834de
+size 4949335224

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68a7d0339933dac106d06ef88cc483ce3b9fad3aeee8c79642ddcefbc9b6c32
+size 4949335224

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d558ba32dde091e9d656523a63d530c6e7554c736220dcf38bf5e74dcb96098
+size 4999675528

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f76812be31ed1c401f776f2f7d210b63bb8c67c0f825680ed9a3af2842ba20
+size 4982898088

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0357c665ef5cade8b8ab6675dc5f4cf42ff3a12d217ffdada33e87f197bf0661
+size 4949335224

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254638ba915e4a679df7d0d676f1dc52bac90cb0d08b45fa441b2b566ad4e4e8
+size 3725640504

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 48319963136}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors", "lm_head.weight": "model-00010-of-00010.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404