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..557302c8a1a0e8bc7384feb24bc7ea4388b1e9cc --- /dev/null +++ b/README.md @@ -0,0 +1,182 @@ +--- +license: mit +language: + - en + - zh +base_model: zai-org/GLM-4.7-Flash +pipeline_tag: text-generation +tags: + - quantized + - Mixture of Experts + - 4-bit + - GPTQ + - MMFP4 + - glm + - metal-marlin + - moe +library_name: transformers +arxiv: "2508.06471" +--- + +# GLM-4.7-Flash-Marlin-MMFP4 + +![](https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/logo.svg) + +**MMFP4-quantized GLM-4.7-Flash** — a 30B-A3B MoE model compressed to **4 bits per weight** using GPTQ with actorder and Metal Marlin's E2M1 FP4 format. + +| Metric | Value | +|--------|-------| +| **Effective bits** | 4.0 bpw | +| **Compression** | 4× vs FP16 | +| **Model size** | ~16 GB (vs ~60 GB FP16) | +| **Parameters** | 29.3B | +| **Format** | HuggingFace sharded safetensors | + +## Model Description + +This is a quantized version of [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash), the strongest model in the 30B class that balances performance and efficiency. + +GLM-4.7-Flash features: + +- **30B-A3B MoE architecture** (64 experts + shared expert, 2-4 active per token) +- **Multi-head Latent Attention (MLA)** for 8× KV cache compression +- **State-of-the-art reasoning** (91.6% on AIME 2025, 59.2% on SWE-bench Verified) +- **Bilingual** (English + Chinese) + +## Quantization Details + +Quantized using **MR-GPTQ** (Metal Marlin GPTQ) with CUDA acceleration: + +### Method + +- **Format**: MMFP4 (E2M1 FP4) — Metal Marlin's native FP4 format +- **Quantization**: GPTQ with actorder (activation-order column permutation) +- **Hessian calibration**: Pre-computed Hessians for attention layers +- **Expert quantization**: Identity Hessian with actorder (no calibration data for MoE experts) +- **Group size**: 128 +- **Hardware**: NVIDIA RTX 3090 Ti (CUDA-accelerated Cholesky factorization) + +### Quantization Statistics + +| Component | Bit Width | Notes | +|-----------|-----------|-------| +| Embeddings | FP16 | Full precision | +| LM Head | FP16 | Full precision | +| Attention (q/k/v/o) | 4-bit | GPTQ with Hessians | +| MoE Experts (64×) | 4-bit | GPTQ with actorder | +| Layer Norms | FP16 | Full precision | +| Router Weights | FP16 | Full precision | + +- **Total tensors**: 19,066 +- **Shards**: 48 safetensors files +- **Quantization time**: ~20 minutes (RTX 3090 Ti) + +## Files + +``` +GLM-4.7-Flash-Marlin-MMFP4/ +├── model-00001-of-00048.safetensors # Layer 0 (embeddings) +├── model-00002-of-00048.safetensors # Layer 1 +├── ... +├── model-00048-of-00048.safetensors # Layer 47 + lm_head +├── model.safetensors.index.json # Weight map +├── config.json # Model config +├── generation_config.json +├── tokenizer.json # Tokenizer +└── tokenizer_config.json +``` + +## Usage + +### With Metal Marlin (Apple Silicon) + +```python +from metal_marlin import MarlinForCausalLM +from transformers import AutoTokenizer + +model = MarlinForCausalLM.from_pretrained( + "RESMP-DEV/GLM-4.7-Flash-Marlin-MMFP4", + device="mps" +) +tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash") + +prompt = "<|user|>\nExplain quantum computing in simple terms.\n<|assistant|>\n" +input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("mps") +output = model.generate(input_ids, max_new_tokens=256, temperature=0.7) +print(tokenizer.decode(output[0], skip_special_tokens=True)) +``` + +### Tensor Format + +Each quantized weight tensor has corresponding scale factors: + +- `{name}.weight`: Packed FP4 weights (uint8) +- `{name}.scales`: FP16 per-group scales (group_size=128) + +## Hardware Requirements + +| Device | Memory | Notes | +|--------|--------|-------| +| Apple M4 Max | 36 GB+ | Via Metal Marlin | +| Apple M2 Ultra | 64 GB+ | Via Metal Marlin | +| NVIDIA RTX 3090 | 24 GB | With offloading | +| NVIDIA RTX 4090 | 24 GB | Native | + +## Benchmarks + +### Original Model Performance (from Z.AI) + +| Benchmark | GLM-4.7-Flash | Qwen3-30B-A3B | GPT-OSS-20B | +|-----------|---------------|---------------|-------------| +| AIME 2025 | **91.6** | 85.0 | 91.7 | +| GPQA | **75.2** | 73.4 | 71.5 | +| SWE-bench Verified | **59.2** | 22.0 | 34.0 | +| τ²-Bench | **79.5** | 49.0 | 47.7 | +| BrowseComp | **42.8** | 2.29 | 28.3 | + +### Quantized Model Notes + +- GPTQ with actorder minimizes quality loss vs RTN +- Expected degradation: ~1-2% on benchmarks vs FP16 +- E2M1 FP4 format optimized for Metal Performance Shaders + +## Comparison with Trellis Quant + +| Model | Format | Size | Bits | Method | +|-------|--------|------|------|--------| +| [GLM-4.7-Flash-Trellis-MM](https://huggingface.co/RESMP-DEV/GLM-4.7-Flash-Trellis-MM) | Trellis | 14 GB | 3.78 bpw | EXL3-style mixed precision | +| **This model** | MMFP4 | 16 GB | 4.0 bpw | GPTQ + actorder | + +Choose **Trellis** for smaller size, **MMFP4** for simpler tensor format and potentially better compatibility. + +## Limitations + +- **Metal Marlin required** for optimal inference on Apple Silicon +- **No speculative decoding** yet +- **Quality loss**: ~1-2% on benchmarks vs FP16 (typical for 4-bit quantization) + +## Credits + +- **Original model**: [Z.AI / GLM Team](https://huggingface.co/zai-org/GLM-4.7-Flash) +- **Quantization method**: GPTQ with actorder +- **Quantization toolkit**: [Metal Marlin](https://github.com/RESMP-DEV/metal-marlin) + +## Citation + +If you use this model, please cite the original GLM-4.5 paper: + +```bibtex +@misc{glm2025glm45, + title={GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models}, + author={GLM Team and Aohan Zeng and Xin Lv and others}, + year={2025}, + eprint={2508.06471}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2508.06471}, +} +``` + +## License + +This quantized model inherits the **MIT License** from the original GLM-4.7-Flash model. diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6637ccbc226eb78776af6a66b6558ce6421be20e --- /dev/null +++ b/config.json @@ -0,0 +1,45 @@ +{ + "architectures": [ + "Glm4MoeLiteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "pad_token_id": 154820, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "hidden_act": "silu", + "hidden_size": 2048, + "intermediate_size": 10240, + "max_position_embeddings": 202752, + "model_type": "glm4_moe_lite", + "moe_intermediate_size": 1536, + "topk_method": "noaux_tc", + "norm_topk_prob": true, + "num_attention_heads": 20, + "n_group": 1, + "topk_group": 1, + "n_routed_experts": 64, + "n_shared_experts": 1, + "routed_scaling_factor": 1.8, + "num_experts_per_tok": 4, + "first_k_dense_replace": 1, + "num_hidden_layers": 47, + "num_key_value_heads": 20, + "num_nextn_predict_layers": 1, + "partial_rotary_factor": 1.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "dtype": "bfloat16", + "transformers_version": "5.0.0rc0", + "q_lora_rank": 768, + "kv_lora_rank": 512, + "qk_nope_head_dim": 192, + "qk_rope_head_dim": 64, + "v_head_dim": 256, + "vocab_size": 154880 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1dfa4cbf88115f19b4c6fcb086cc5669d2ce5e57 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "pad_token_id": 154820, + "temperature": 1.0, + "transformers_version": "5.0.0.dev0" +} diff --git a/model-00001-of-00048.safetensors b/model-00001-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a754be7deab529649985f0a49e2a71387bf5e22 --- /dev/null +++ b/model-00001-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c75eac1933aefdf174d6248f129c47b8f824380d67ac16d7cb5a6147926d69 +size 43672248 diff --git a/model-00002-of-00048.safetensors b/model-00002-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e893710afe17b7da74f87d99953c855709191791 --- /dev/null +++ b/model-00002-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f1b7a84f2090d15ee804ef8d548177f8b82b6ec7965ced8188988f3bb3a87d +size 327833240 diff --git a/model-00003-of-00048.safetensors b/model-00003-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6e3fe5d65bd789456dc1083a39d4334ebc1b90b --- /dev/null +++ b/model-00003-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ecdc9ce4adb8c055d01b87d64076ad728ff68e666dc928e03da78bac377c920 +size 327833240 diff --git a/model-00004-of-00048.safetensors b/model-00004-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73a4acc3f629e91dda32d5f6fc32e97a99f65c50 --- /dev/null +++ b/model-00004-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b006af82949a3315aef90b7baf1a2a9882bb3f43f9ce3c8cd65b4c76c9e38207 +size 327833240 diff --git a/model-00005-of-00048.safetensors b/model-00005-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27f2c9aae1c0b9e129c2411737f821a64cf3330a --- /dev/null +++ b/model-00005-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3e9ef0665b550cb3372a710f8821dc0a1a92064659d387638a5ecb40ca9884 +size 327833240 diff --git a/model-00006-of-00048.safetensors b/model-00006-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b1c17ec1eac8b4bf3ef112d5bace6376ac8b867 --- /dev/null +++ b/model-00006-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a5e3764b1084fd6b83adf38607d33f086c3940f9fa058b0e45db98f47fda0c +size 327833240 diff --git a/model-00007-of-00048.safetensors b/model-00007-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68d2613920e40ef54ead6d528efa36f167b7b405 --- /dev/null +++ b/model-00007-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe2dc6014f82667508eb8a83a3e784507d1a9848326777dbf93b3c8b9cf64d5 +size 327833240 diff --git a/model-00008-of-00048.safetensors b/model-00008-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..149937dc1ee4ca5d730fbbd0e5f580f4d484e0da --- /dev/null +++ b/model-00008-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7aeadd95910d968c8865af1512c273b50ae3b52487c5a8844d198ed8ed1c94 +size 327833240 diff --git a/model-00009-of-00048.safetensors b/model-00009-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86e7aded8cfe9c055c991ba236fe2f6bfc265901 --- /dev/null +++ b/model-00009-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37a52a176a1055b54499d69790be9e6d002d292a1f279e191b0bc0e78ebf6d4 +size 327833240 diff --git a/model-00010-of-00048.safetensors b/model-00010-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64c8e77ec298c0e5efc6c367a72e4681c3554cdf --- /dev/null +++ b/model-00010-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc713771ef57f3f1a2ddddbc8975840b039009211af61283f317fe82f3b0f803 +size 327833240 diff --git a/model-00011-of-00048.safetensors b/model-00011-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e92d4b42a146bc39bdf7bd23d96bd2a3cf0f079 --- /dev/null +++ b/model-00011-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9d3ea9e470875dc56792322a46722b6512fd3297cb6cd278f3946e72dc1b57 +size 327833648 diff --git a/model-00012-of-00048.safetensors b/model-00012-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..032f05265a69437c48483224410616c51badf6d4 --- /dev/null +++ b/model-00012-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed7dd635f55f86789b8ad28da9b2f7e35720711e22b90c9a3b6d5238beb9e10 +size 327833648 diff --git a/model-00013-of-00048.safetensors b/model-00013-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c68370f3809e69b69f56612ce7aaafef0ca938e7 --- /dev/null +++ b/model-00013-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826e321f91601aa166993da7a792b2e1e31b9de8eac98ea3c629bec6edae15bc +size 327833648 diff --git a/model-00014-of-00048.safetensors b/model-00014-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f161a21dc2899b5c9050e3a3344f0326e59c913 --- /dev/null +++ b/model-00014-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b088ccb049f761d50f94ed9688929a046990b4ff9b9728fe4e4f6a8afe99c8 +size 327833648 diff --git a/model-00015-of-00048.safetensors b/model-00015-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3aecc23ce087ee57daeeebf983451aefd53683b --- /dev/null +++ b/model-00015-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf329d81710a99098bebd05de1d809174a9c7ad2ef508845b07416f1ba8a938b +size 327833648 diff --git a/model-00016-of-00048.safetensors b/model-00016-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..645ce6f010c4bf1a6795ffee07094d15072ce7ab --- /dev/null +++ b/model-00016-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bcea67819f6c8d448ad70dfd65ee40cdcf025732a94c20cf8c845013a4fd90 +size 327833648 diff --git a/model-00017-of-00048.safetensors b/model-00017-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..283c71cdaf2101454f1c4642d52f60197b72d9d6 --- /dev/null +++ b/model-00017-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8136af0e71dd04218a927dbf44b415c93160df2fa9299db978bb0d82e0c82e5b +size 327833648 diff --git a/model-00018-of-00048.safetensors b/model-00018-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e13dc703cf398893b254153d0a6f15bb3a3849e --- /dev/null +++ b/model-00018-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b27e105f72ddf7a01b1ab864ce664a8d3d232880e3ff380a626e20fd63dafe3 +size 327833648 diff --git a/model-00019-of-00048.safetensors b/model-00019-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f5e2ea79f04aa990aaab761075d726c3382759c0 --- /dev/null +++ b/model-00019-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6f39fcfccbc3e9a4333bd484ac12cd816dc2c6fc266fc357e42a4a773ae051 +size 327833648 diff --git a/model-00020-of-00048.safetensors b/model-00020-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d0dfcd79fc3805afdf79bd1c7774e28cb78f161 --- /dev/null +++ b/model-00020-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:660343ac01528ac8d18ca2d2e1af3158c23adb215284a724c619b074980ae42f +size 327833648 diff --git a/model-00021-of-00048.safetensors b/model-00021-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ceda898c8e6e01d7e1513c819dfa12a0b9445285 --- /dev/null +++ b/model-00021-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:279237957148596abb9ce53e783e4583b3ac99ff6270cbe2242202f18891cc5d +size 327833648 diff --git a/model-00022-of-00048.safetensors b/model-00022-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..334d8e2c603ac41cd3d1b3170c5ac394cdb22ec9 --- /dev/null +++ b/model-00022-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350d4635ff553896c5a193f12721042083d2741baa34e4cb7fc2e4dd608e144d +size 327833648 diff --git a/model-00023-of-00048.safetensors b/model-00023-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80e5b8995af7afee82c5030016cd4171f4ab7394 --- /dev/null +++ b/model-00023-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0cd17264aeac8156ff8b620f759d5a6c4fa9fb376b31950f28935720320859 +size 327833648 diff --git a/model-00024-of-00048.safetensors b/model-00024-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..defed3075342d57139257b728d6bd32187e9a33f --- /dev/null +++ b/model-00024-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e1bb3f7ecfb31ad86e0ca08eb7272b79041750a3d37e3fa53406746ffaed4fd +size 327833648 diff --git a/model-00025-of-00048.safetensors b/model-00025-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..924de2a652f7ce26e4130c897b7f14648bcc8880 --- /dev/null +++ b/model-00025-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636c23bd06de9f265e7bd504de64f6b6f52d129a425dbab7eeaffa7854119ada +size 327833648 diff --git a/model-00026-of-00048.safetensors b/model-00026-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48623733e1922b938d2cd646dd398fcfceac6934 --- /dev/null +++ b/model-00026-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd142bfc41b48bcf30f173febf3b425aa640aa2a87a88dc418948b0686437fb3 +size 327833648 diff --git a/model-00027-of-00048.safetensors b/model-00027-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c019a3821caa8ef6820df572ccc171c5c9afc992 --- /dev/null +++ b/model-00027-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d684936b534f4da73488c37df32177b5f19fd7a349431bdb0b0edfe6f6567c +size 327833648 diff --git a/model-00028-of-00048.safetensors b/model-00028-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ffd49ada1ab2884e0b871d8c1e2ac30376a6962 --- /dev/null +++ b/model-00028-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17abe4e3ef81c14065300e33198a44237ac51880f383912f1cf3200d69e2dee6 +size 327833648 diff --git a/model-00029-of-00048.safetensors b/model-00029-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b237a55377b27ec68c2accfd95dccb99d7bc35b3 --- /dev/null +++ b/model-00029-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2311764b9408632af65ae0dc21b5f0353986c3c47a0031a626098df65fc05d +size 327833648 diff --git a/model-00030-of-00048.safetensors b/model-00030-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c9a012072a8d8acf49cd22c1c387330990a7220 --- /dev/null +++ b/model-00030-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b03130258c4c6c60026ceb61e0190020da76a0b9aef48e7f761932d7c656ce +size 327833648 diff --git a/model-00031-of-00048.safetensors b/model-00031-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b611ded8f3824f701154aa77fab816d8860360b6 --- /dev/null +++ b/model-00031-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae64f3e55603f1a1e3a9d2fce50fb88a547d66f27acb31f8043a93eb97dbb2ee +size 327833648 diff --git a/model-00032-of-00048.safetensors b/model-00032-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7abe9263c74985623256fcd72386bf98997a7665 --- /dev/null +++ b/model-00032-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21366f8b23ed73d2bcf75bdbab9c0122f17abed308b6ba3319060b9bc8f0adc +size 327833648 diff --git a/model-00033-of-00048.safetensors b/model-00033-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0e3a86516aaf9b52effe1c835c40e1eefeba719 --- /dev/null +++ b/model-00033-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa7c2cfe969844ff866c80c7c46dee90de2abac06b886b246550a2b53bbbc25 +size 327833648 diff --git a/model-00034-of-00048.safetensors b/model-00034-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0eae62b5cd2fe679c2f46dd9aa5089112362a3a --- /dev/null +++ b/model-00034-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7c93ce6893a3cc825987ca92c197261464e903506af51779ae5df5d50972f3 +size 327833648 diff --git a/model-00035-of-00048.safetensors b/model-00035-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ab37b594646a3aa2a3782897e55a23f91faecc7 --- /dev/null +++ b/model-00035-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328c8c578a97cd6d37518f953613c22123f2f4de1475d7777fd3ea8b6b7f5163 +size 327833648 diff --git a/model-00036-of-00048.safetensors b/model-00036-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c25b4857d1649dee4796abda0c22ac319370b30 --- /dev/null +++ b/model-00036-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92cce91528e2230b446321c5aff6d543812512a3eb00acb80944c82aee588752 +size 327833648 diff --git a/model-00037-of-00048.safetensors b/model-00037-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc661248c38a5520e166b8666ec8915a6d83436f --- /dev/null +++ b/model-00037-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb2b3661d4333703c1e7d6ed30ecdc94a24e9c7a45ea390166c24cceb01ce9a +size 327833648 diff --git a/model-00038-of-00048.safetensors b/model-00038-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9496b2eb17da625f591e9a40c8c0966921215e06 --- /dev/null +++ b/model-00038-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfce66c57e056ff78615e0ee624bd49bc88c1dba1eb23b9c64bbb732b48d6a7f +size 327833648 diff --git a/model-00039-of-00048.safetensors b/model-00039-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cda42384714810514a7aa28cc0a8527e11bfcc8f --- /dev/null +++ b/model-00039-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771f8155c915eeeb5c1f1f38c44e3f3cb37be4b9be5c287bb3db5f8cca95f932 +size 327833648 diff --git a/model-00040-of-00048.safetensors b/model-00040-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4dc88d1663056217d57299e90ea9ea51928a580f --- /dev/null +++ b/model-00040-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9369d29ce83807e45840032a764473a8d4e6338497351b97b5a98ad01fbb9fea +size 327833648 diff --git a/model-00041-of-00048.safetensors b/model-00041-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4086020779f2ddb06c14c9b6af9e2c649f1394cb --- /dev/null +++ b/model-00041-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fb20256de1f464af76e118ba3da9344f464f54164dec7179c3e5517ccb1ba6 +size 327833648 diff --git a/model-00042-of-00048.safetensors b/model-00042-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b84c55f4fbfa05d06c4b83569f749c4c6ac3b489 --- /dev/null +++ b/model-00042-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd23a8ca75ce66417c60e2b562476fc85d73d80f61034f1e178fc4594e37f8dc +size 327833648 diff --git a/model-00043-of-00048.safetensors b/model-00043-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6696f854c3f3738066708f960397a0ae175f20bd --- /dev/null +++ b/model-00043-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11bafe4c66fd086814c5c0427f3699d7a1b1f2749a563853cd54bfcf4c2b1bc2 +size 327833648 diff --git a/model-00044-of-00048.safetensors b/model-00044-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80ea25fc43a2175ea956c46c275c81decf9756b1 --- /dev/null +++ b/model-00044-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608d8caec230802251d6283475815be2939140e969d559c63f37502da7f28d9b +size 327833648 diff --git a/model-00045-of-00048.safetensors b/model-00045-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3049512b1967c10d9b6f574360eb0c092c8d8d43 --- /dev/null +++ b/model-00045-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256ee66546a588a35ff7d67ef48e1766989e53f579b6db736fa6ae40098bf7d0 +size 327833648 diff --git a/model-00046-of-00048.safetensors b/model-00046-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c49eb5bbe7d22fafdcbc45566c52e82326eb33b --- /dev/null +++ b/model-00046-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0b38005a15ee13d81fa77971c50ff541d18db75e20d948eed4484a26689bf3 +size 327833648 diff --git a/model-00047-of-00048.safetensors b/model-00047-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78565fe260d7b26fa9a26f22a2b6265c119afafe --- /dev/null +++ b/model-00047-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcf88018628937d66e37ceb8b74107c305a9a003737492ed9bbff8a2b319b66 +size 327833648 diff --git a/model-00048-of-00048.safetensors b/model-00048-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39e5e6f98baf30d3458c7689ca61711fa5878b73 --- /dev/null +++ b/model-00048-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd4ed027bd7754db3dad02ac7d2099e2700b47be86a5d3a13bf9273a555cc8f +size 1268777160 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..144cda82269fc34c25f48bd5ae5ae79dd04a39cd --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,19075 @@ +{ + "metadata": { + "format": "mmfp4" + }, + "weight_map": { + "model.layers.47.eh_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.eh_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.enorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.hnorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.input_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.0.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.1.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.10.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.11.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.12.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.13.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.14.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.15.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.16.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.17.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.18.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.19.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.2.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.20.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.21.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.22.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.23.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.24.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.25.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.26.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.27.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.28.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.29.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.3.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.30.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.31.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.32.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.33.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.34.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.35.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.36.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.37.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.38.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.39.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.4.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.40.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.41.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.42.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.43.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.44.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.45.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.46.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.47.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.48.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.49.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.5.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.50.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.51.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.52.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.53.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.54.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.55.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.56.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.57.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.58.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.59.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.6.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.60.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.61.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.62.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.63.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.7.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.8.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.experts.9.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00047-of-00048.safetensors", + "model.layers.47.mlp.gate.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_proj_with_mqa.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_a_proj_with_mqa.scales": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_b_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.kv_b_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_layernorm.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_a_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_b_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.47.self_attn.q_b_proj.scales": "model-00048-of-00048.safetensors", + "model.layers.47.shared_head.head.weight": "model-00048-of-00048.safetensors", + "model.layers.47.shared_head.head.scales": "model-00048-of-00048.safetensors", + "model.layers.47.shared_head.norm.weight": "model-00048-of-00048.safetensors", + "model.norm.weight": "model-00047-of-00048.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.kv_b_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_a_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_b_proj.scales": "model-00001-of-00048.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.0.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.1.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.10.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.11.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.12.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.13.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.14.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.15.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.16.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.17.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.18.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.19.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.2.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.20.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.21.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.22.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.23.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.24.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.25.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.26.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.27.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.28.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.29.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.3.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.30.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.31.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.32.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.33.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.34.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.35.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.36.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.37.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.38.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.39.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.4.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.40.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.41.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.42.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.43.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.44.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.45.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.46.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.47.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.48.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.49.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.5.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.50.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.51.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.52.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.53.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.54.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.55.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.56.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.57.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.58.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.59.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.6.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.60.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.61.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.62.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.63.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.7.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.8.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.experts.9.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_b_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.kv_b_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_a_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_b_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_b_proj.scales": "model-00002-of-00048.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.0.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.1.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.10.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.11.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.12.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.13.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.14.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.15.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.16.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.17.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.18.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.19.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.2.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.20.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.21.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.22.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.23.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.24.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.25.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.26.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.27.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.28.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.29.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.3.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.30.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.31.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.32.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.33.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.34.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.35.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.36.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.37.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.38.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.39.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.4.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.40.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.41.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.42.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.43.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.44.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.45.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.46.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.47.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.48.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.49.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.5.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.50.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.51.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.52.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.53.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.54.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.55.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.56.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.57.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.58.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.59.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.6.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.60.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.61.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.62.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.63.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.7.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.8.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.experts.9.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_b_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.kv_b_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_a_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_b_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_b_proj.scales": "model-00003-of-00048.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.0.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.1.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.10.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.11.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.12.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.13.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.14.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.15.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.16.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.17.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.18.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.19.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.2.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.20.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.21.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.22.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.23.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.24.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.25.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.26.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.27.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.28.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.29.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.3.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.30.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.31.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.32.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.33.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.34.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.35.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.36.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.37.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.38.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.39.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.4.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.40.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.41.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.42.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.43.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.44.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.45.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.46.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.47.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.48.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.49.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.5.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.50.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.51.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.52.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.53.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.54.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.55.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.56.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.57.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.58.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.59.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.6.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.60.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.61.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.62.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.63.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.7.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.8.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.experts.9.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_b_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.kv_b_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_a_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_b_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.q_b_proj.scales": "model-00004-of-00048.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.0.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.1.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.10.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.11.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.12.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.13.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.14.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.15.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.16.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.17.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.18.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.19.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.2.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.20.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.21.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.22.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.23.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.24.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.25.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.26.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.27.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.28.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.29.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.3.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.30.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.31.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.32.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.33.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.34.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.35.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.36.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.37.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.38.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.39.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.4.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.40.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.41.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.42.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.43.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.44.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.45.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.46.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.47.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.48.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.49.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.5.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.50.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.51.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.52.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.53.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.54.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.55.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.56.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.57.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.58.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.59.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.6.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.60.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.61.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.62.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.63.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.7.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.8.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.experts.9.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_b_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.kv_b_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_a_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_b_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.4.self_attn.q_b_proj.scales": "model-00005-of-00048.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.0.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.1.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.10.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.11.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.12.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.13.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.14.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.15.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.16.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.17.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.18.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.19.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.2.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.20.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.21.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.22.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.23.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.24.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.25.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.26.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.27.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.28.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.29.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.3.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.30.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.31.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.32.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.33.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.34.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.35.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.36.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.37.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.38.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.39.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.4.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.40.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.41.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.42.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.43.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.44.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.45.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.46.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.47.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.48.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.49.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.5.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.50.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.51.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.52.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.53.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.54.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.55.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.56.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.57.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.58.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.59.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.6.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.60.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.61.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.62.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.63.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.7.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.8.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.experts.9.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_b_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.kv_b_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_a_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_b_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.5.self_attn.q_b_proj.scales": "model-00006-of-00048.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.0.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.1.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.10.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.11.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.12.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.13.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.14.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.15.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.16.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.17.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.18.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.19.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.2.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.20.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.21.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.22.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.23.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.24.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.25.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.26.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.27.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.28.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.29.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.3.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.30.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.31.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.32.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.33.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.34.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.35.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.36.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.37.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.38.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.39.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.4.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.40.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.41.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.42.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.43.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.44.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.45.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.46.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.47.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.48.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.49.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.5.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.50.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.51.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.52.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.53.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.54.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.55.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.56.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.57.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.58.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.59.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.6.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.60.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.61.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.62.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.63.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.7.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.8.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.experts.9.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_a_proj_with_mqa.scales": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_b_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.kv_b_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_a_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_b_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.6.self_attn.q_b_proj.scales": "model-00007-of-00048.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.0.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.1.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.10.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.11.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.12.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.13.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.14.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.15.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.16.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.17.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.18.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.19.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.2.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.20.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.21.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.22.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.23.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.24.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.25.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.26.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.27.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.28.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.29.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.3.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.30.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.31.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.32.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.33.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.34.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.35.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.36.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.37.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.38.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.39.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.4.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.40.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.41.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.42.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.43.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.44.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.45.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.46.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.47.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.48.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.49.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.5.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.50.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.51.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.52.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.53.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.54.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.55.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.56.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.57.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.58.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.59.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.6.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.60.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.61.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.62.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.63.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.7.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.8.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.experts.9.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_b_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.kv_b_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_a_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_b_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.7.self_attn.q_b_proj.scales": "model-00008-of-00048.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.0.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.1.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.10.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.11.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.12.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.13.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.14.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.15.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.16.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.17.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.18.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.19.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.2.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.20.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.21.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.22.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.23.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.24.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.25.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.26.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.27.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.28.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.29.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.3.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.30.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.31.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.32.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.33.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.34.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.35.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.36.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.37.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.38.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.39.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.4.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.40.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.41.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.42.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.43.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.44.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.45.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.46.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.47.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.48.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.49.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.5.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.50.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.51.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.52.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.53.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.54.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.55.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.56.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.57.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.58.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.59.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.6.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.60.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.61.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.62.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.63.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.7.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.8.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.experts.9.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_a_proj_with_mqa.scales": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_b_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.kv_b_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_a_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_b_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.8.self_attn.q_b_proj.scales": "model-00009-of-00048.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.0.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.1.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.10.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.11.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.12.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.13.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.14.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.15.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.16.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.17.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.18.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.19.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.2.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.20.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.21.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.22.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.23.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.24.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.25.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.26.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.27.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.28.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.29.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.3.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.30.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.31.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.32.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.33.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.34.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.35.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.36.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.37.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.38.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.39.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.4.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.40.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.41.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.42.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.43.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.44.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.45.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.46.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.47.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.48.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.49.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.5.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.50.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.51.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.52.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.53.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.54.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.55.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.56.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.57.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.58.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.59.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.6.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.60.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.61.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.62.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.63.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.7.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.8.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.experts.9.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_a_proj_with_mqa.scales": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_b_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.kv_b_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_a_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_b_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.9.self_attn.q_b_proj.scales": "model-00010-of-00048.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.0.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.1.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.10.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.11.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.12.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.13.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.14.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.15.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.16.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.17.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.18.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.19.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.2.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.20.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.21.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.22.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.23.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.24.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.25.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.26.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.27.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.28.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.29.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.3.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.30.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.31.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.32.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.33.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.34.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.35.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.36.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.37.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.38.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.39.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.4.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.40.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.41.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.42.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.43.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.44.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.45.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.46.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.47.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.48.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.49.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.5.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.50.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.51.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.52.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.53.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.54.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.55.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.56.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.57.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.58.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.59.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.6.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.60.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.61.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.62.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.63.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.7.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.8.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.experts.9.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_a_proj_with_mqa.scales": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_b_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.kv_b_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_a_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_b_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.10.self_attn.q_b_proj.scales": "model-00011-of-00048.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.0.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.1.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.10.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.11.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.12.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.13.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.14.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.15.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.16.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.17.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.18.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.19.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.2.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.20.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.21.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.22.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.23.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.24.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.25.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.26.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.27.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.28.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.29.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.3.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.30.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.31.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.32.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.33.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.34.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.35.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.36.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.37.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.38.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.39.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.4.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.40.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.41.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.42.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.43.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.44.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.45.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.46.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.47.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.48.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.49.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.5.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.50.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.51.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.52.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.53.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.54.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.55.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.56.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.57.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.58.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.59.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.6.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.60.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.61.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.62.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.63.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.7.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.8.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.experts.9.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_b_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.kv_b_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_a_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_b_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.11.self_attn.q_b_proj.scales": "model-00012-of-00048.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.0.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.1.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.10.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.11.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.12.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.13.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.14.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.15.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.16.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.17.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.18.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.19.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.2.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.20.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.21.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.22.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.23.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.24.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.25.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.26.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.27.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.28.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.29.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.3.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.30.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.31.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.32.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.33.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.34.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.35.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.36.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.37.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.38.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.39.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.4.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.40.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.41.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.42.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.43.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.44.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.45.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.46.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.47.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.48.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.49.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.5.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.50.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.51.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.52.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.53.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.54.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.55.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.56.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.57.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.58.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.59.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.6.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.60.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.61.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.62.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.63.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.7.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.8.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.experts.9.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_a_proj_with_mqa.scales": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_b_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.kv_b_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_a_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_b_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.12.self_attn.q_b_proj.scales": "model-00013-of-00048.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.0.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.1.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.10.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.11.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.12.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.13.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.14.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.15.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.16.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.17.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.18.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.19.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.2.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.20.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.21.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.22.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.23.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.24.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.25.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.26.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.27.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.28.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.29.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.3.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.30.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.31.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.32.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.33.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.34.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.35.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.36.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.37.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.38.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.39.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.4.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.40.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.41.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.42.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.43.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.44.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.45.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.46.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.47.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.48.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.49.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.5.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.50.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.51.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.52.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.53.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.54.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.55.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.56.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.57.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.58.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.59.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.6.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.60.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.61.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.62.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.63.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.7.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.8.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.experts.9.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_a_proj_with_mqa.scales": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_b_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.kv_b_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_a_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_b_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.13.self_attn.q_b_proj.scales": "model-00014-of-00048.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.0.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.1.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.10.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.11.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.12.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.13.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.14.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.15.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.16.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.17.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.18.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.19.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.2.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.20.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.21.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.22.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.23.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.24.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.25.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.26.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.27.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.28.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.29.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.3.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.30.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.31.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.32.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.33.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.34.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.35.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.36.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.37.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.38.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.39.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.4.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.40.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.41.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.42.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.43.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.44.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.45.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.46.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.47.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.48.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.49.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.5.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.50.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.51.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.52.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.53.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.54.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.55.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.56.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.57.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.58.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.59.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.6.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.60.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.61.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.62.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.63.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.7.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.8.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.experts.9.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_b_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.kv_b_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_a_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_b_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.14.self_attn.q_b_proj.scales": "model-00015-of-00048.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.0.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.1.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.10.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.11.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.12.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.13.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.14.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.15.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.16.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.17.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.18.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.19.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.2.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.20.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.21.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.22.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.23.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.24.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.25.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.26.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.27.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.28.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.29.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.3.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.30.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.31.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.32.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.33.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.34.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.35.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.36.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.37.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.38.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.39.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.4.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.40.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.41.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.42.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.43.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.44.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.45.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.46.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.47.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.48.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.49.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.5.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.50.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.51.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.52.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.53.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.54.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.55.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.56.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.57.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.58.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.59.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.6.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.60.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.61.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.62.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.63.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.7.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.8.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.experts.9.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_b_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.kv_b_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_a_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_b_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.15.self_attn.q_b_proj.scales": "model-00016-of-00048.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.0.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.1.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.10.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.11.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.12.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.13.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.14.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.15.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.16.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.17.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.18.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.19.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.2.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.20.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.21.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.22.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.23.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.24.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.25.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.26.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.27.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.28.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.29.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.3.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.30.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.31.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.32.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.33.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.34.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.35.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.36.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.37.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.38.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.39.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.4.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.40.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.41.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.42.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.43.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.44.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.45.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.46.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.47.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.48.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.49.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.5.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.50.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.51.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.52.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.53.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.54.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.55.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.56.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.57.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.58.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.59.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.6.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.60.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.61.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.62.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.63.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.7.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.8.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.experts.9.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_b_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.kv_b_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_a_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_b_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.16.self_attn.q_b_proj.scales": "model-00017-of-00048.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.0.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.1.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.10.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.11.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.12.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.13.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.14.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.15.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.16.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.17.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.18.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.19.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.2.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.20.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.21.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.22.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.23.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.24.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.25.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.26.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.27.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.28.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.29.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.3.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.30.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.31.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.32.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.33.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.34.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.35.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.36.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.37.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.38.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.39.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.4.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.40.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.41.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.42.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.43.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.44.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.45.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.46.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.47.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.48.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.49.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.5.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.50.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.51.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.52.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.53.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.54.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.55.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.56.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.57.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.58.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.59.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.6.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.60.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.61.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.62.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.63.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.7.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.8.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.experts.9.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_b_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.kv_b_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_a_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_b_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.17.self_attn.q_b_proj.scales": "model-00018-of-00048.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.0.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.1.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.10.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.11.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.12.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.13.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.14.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.15.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.16.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.17.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.18.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.19.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.2.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.20.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.21.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.22.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.23.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.24.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.25.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.26.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.27.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.28.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.29.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.3.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.30.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.31.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.32.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.33.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.34.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.35.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.36.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.37.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.38.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.39.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.4.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.40.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.41.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.42.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.43.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.44.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.45.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.46.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.47.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.48.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.49.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.5.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.50.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.51.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.52.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.53.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.54.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.55.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.56.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.57.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.58.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.59.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.6.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.60.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.61.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.62.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.63.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.7.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.8.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.experts.9.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_b_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.kv_b_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_a_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_b_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.18.self_attn.q_b_proj.scales": "model-00019-of-00048.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.0.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.1.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.10.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.11.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.12.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.13.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.14.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.15.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.16.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.17.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.18.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.19.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.2.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.20.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.21.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.22.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.23.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.24.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.25.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.26.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.27.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.28.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.29.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.3.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.30.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.31.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.32.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.33.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.34.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.35.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.36.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.37.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.38.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.39.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.4.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.40.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.41.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.42.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.43.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.44.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.45.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.46.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.47.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.48.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.49.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.5.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.50.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.51.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.52.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.53.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.54.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.55.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.56.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.57.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.58.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.59.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.6.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.60.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.61.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.62.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.63.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.7.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.8.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.experts.9.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_b_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.kv_b_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_a_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_b_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.19.self_attn.q_b_proj.scales": "model-00020-of-00048.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.0.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.1.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.10.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.11.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.12.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.13.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.14.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.15.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.16.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.17.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.18.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.19.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.2.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.20.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.21.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.22.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.23.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.24.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.25.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.26.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.27.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.28.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.29.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.3.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.30.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.31.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.32.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.33.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.34.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.35.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.36.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.37.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.38.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.39.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.4.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.40.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.41.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.42.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.43.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.44.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.45.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.46.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.47.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.48.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.49.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.5.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.50.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.51.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.52.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.53.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.54.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.55.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.56.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.57.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.58.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.59.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.6.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.60.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.61.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.62.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.63.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.7.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.8.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.experts.9.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_b_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.kv_b_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_a_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_b_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.20.self_attn.q_b_proj.scales": "model-00021-of-00048.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.0.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.1.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.10.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.11.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.12.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.13.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.14.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.15.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.16.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.17.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.18.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.19.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.2.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.20.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.21.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.22.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.23.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.24.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.25.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.26.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.27.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.28.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.29.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.3.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.30.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.31.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.32.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.33.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.34.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.35.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.36.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.37.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.38.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.39.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.4.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.40.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.41.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.42.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.43.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.44.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.45.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.46.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.47.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.48.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.49.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.5.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.50.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.51.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.52.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.53.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.54.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.55.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.56.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.57.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.58.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.59.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.6.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.60.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.61.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.62.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.63.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.7.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.8.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.experts.9.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_b_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.kv_b_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_a_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_b_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.21.self_attn.q_b_proj.scales": "model-00022-of-00048.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.0.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.1.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.10.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.11.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.12.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.13.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.14.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.15.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.16.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.17.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.18.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.19.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.2.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.20.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.21.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.22.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.23.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.24.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.25.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.26.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.27.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.28.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.29.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.3.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.30.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.31.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.32.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.33.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.34.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.35.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.36.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.37.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.38.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.39.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.4.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.40.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.41.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.42.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.43.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.44.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.45.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.46.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.47.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.48.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.49.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.5.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.50.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.51.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.52.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.53.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.54.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.55.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.56.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.57.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.58.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.59.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.6.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.60.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.61.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.62.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.63.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.7.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.8.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.experts.9.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_b_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.kv_b_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_a_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_b_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.22.self_attn.q_b_proj.scales": "model-00023-of-00048.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.0.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.1.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.10.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.11.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.12.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.13.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.14.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.15.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.16.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.17.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.18.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.19.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.2.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.20.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.21.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.22.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.23.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.24.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.25.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.26.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.27.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.28.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.29.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.3.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.30.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.31.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.32.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.33.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.34.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.35.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.36.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.37.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.38.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.39.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.4.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.40.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.41.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.42.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.43.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.44.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.45.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.46.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.47.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.48.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.49.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.5.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.50.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.51.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.52.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.53.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.54.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.55.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.56.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.57.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.58.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.59.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.6.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.60.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.61.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.62.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.63.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.7.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.8.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.experts.9.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_b_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.kv_b_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_a_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_b_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.23.self_attn.q_b_proj.scales": "model-00024-of-00048.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.0.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.1.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.10.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.11.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.12.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.13.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.14.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.15.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.16.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.17.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.18.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.19.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.2.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.20.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.21.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.22.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.23.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.24.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.25.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.26.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.27.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.28.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.29.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.3.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.30.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.31.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.32.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.33.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.34.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.35.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.36.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.37.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.38.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.39.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.4.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.40.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.41.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.42.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.43.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.44.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.45.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.46.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.47.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.48.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.49.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.5.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.50.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.51.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.52.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.53.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.54.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.55.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.56.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.57.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.58.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.59.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.6.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.60.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.61.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.62.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.63.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.7.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.8.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.experts.9.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_b_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.kv_b_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_a_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_b_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.24.self_attn.q_b_proj.scales": "model-00025-of-00048.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.0.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.1.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.10.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.11.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.12.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.13.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.14.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.15.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.16.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.17.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.18.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.19.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.2.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.20.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.21.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.22.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.23.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.24.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.25.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.26.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.27.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.28.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.29.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.3.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.30.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.31.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.32.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.33.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.34.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.35.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.36.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.37.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.38.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.39.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.4.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.40.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.41.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.42.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.43.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.44.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.45.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.46.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.47.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.48.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.49.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.5.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.50.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.51.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.52.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.53.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.54.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.55.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.56.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.57.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.58.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.59.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.6.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.60.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.61.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.62.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.63.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.7.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.8.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.experts.9.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_b_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.kv_b_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_a_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_b_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.25.self_attn.q_b_proj.scales": "model-00026-of-00048.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.0.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.1.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.10.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.11.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.12.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.13.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.14.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.15.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.16.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.17.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.18.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.19.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.2.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.20.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.21.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.22.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.23.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.24.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.25.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.26.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.27.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.28.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.29.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.3.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.30.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.31.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.32.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.33.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.34.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.35.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.36.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.37.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.38.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.39.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.4.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.40.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.41.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.42.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.43.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.44.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.45.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.46.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.47.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.48.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.49.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.5.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.50.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.51.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.52.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.53.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.54.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.55.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.56.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.57.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.58.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.59.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.6.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.60.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.61.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.62.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.63.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.7.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.8.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.experts.9.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_b_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.kv_b_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_a_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_b_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.26.self_attn.q_b_proj.scales": "model-00027-of-00048.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.0.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.1.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.10.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.11.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.12.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.13.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.14.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.15.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.16.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.17.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.18.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.19.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.2.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.20.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.21.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.22.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.23.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.24.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.25.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.26.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.27.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.28.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.29.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.3.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.30.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.31.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.32.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.33.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.34.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.35.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.36.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.37.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.38.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.39.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.4.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.40.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.41.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.42.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.43.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.44.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.45.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.46.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.47.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.48.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.49.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.5.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.50.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.51.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.52.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.53.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.54.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.55.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.56.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.57.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.58.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.59.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.6.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.60.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.61.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.62.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.63.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.7.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.8.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.experts.9.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_a_proj_with_mqa.scales": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_b_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.kv_b_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_a_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_b_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.27.self_attn.q_b_proj.scales": "model-00028-of-00048.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.0.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.1.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.10.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.11.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.12.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.13.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.14.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.15.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.16.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.17.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.18.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.19.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.2.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.20.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.21.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.22.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.23.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.24.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.25.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.26.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.27.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.28.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.29.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.3.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.30.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.31.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.32.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.33.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.34.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.35.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.36.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.37.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.38.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.39.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.4.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.40.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.41.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.42.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.43.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.44.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.45.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.46.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.47.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.48.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.49.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.5.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.50.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.51.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.52.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.53.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.54.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.55.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.56.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.57.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.58.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.59.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.6.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.60.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.61.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.62.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.63.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.7.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.8.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.experts.9.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_a_proj_with_mqa.scales": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_b_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.kv_b_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_a_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_b_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.28.self_attn.q_b_proj.scales": "model-00029-of-00048.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.0.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.1.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.10.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.11.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.12.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.13.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.14.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.15.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.16.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.17.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.18.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.19.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.2.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.20.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.21.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.22.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.23.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.24.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.25.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.26.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.27.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.28.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.29.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.3.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.30.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.31.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.32.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.33.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.34.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.35.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.36.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.37.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.38.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.39.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.4.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.40.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.41.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.42.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.43.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.44.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.45.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.46.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.47.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.48.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.49.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.5.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.50.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.51.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.52.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.53.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.54.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.55.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.56.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.57.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.58.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.59.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.6.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.60.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.61.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.62.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.63.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.7.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.8.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.experts.9.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_a_proj_with_mqa.scales": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_b_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.kv_b_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_a_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_b_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.29.self_attn.q_b_proj.scales": "model-00030-of-00048.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.0.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.1.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.10.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.11.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.12.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.13.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.14.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.15.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.16.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.17.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.18.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.19.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.2.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.20.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.21.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.22.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.23.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.24.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.25.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.26.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.27.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.28.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.29.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.3.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.30.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.31.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.32.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.33.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.34.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.35.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.36.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.37.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.38.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.39.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.4.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.40.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.41.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.42.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.43.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.44.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.45.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.46.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.47.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.48.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.49.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.5.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.50.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.51.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.52.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.53.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.54.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.55.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.56.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.57.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.58.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.59.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.6.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.60.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.61.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.62.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.63.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.7.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.8.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.experts.9.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_a_proj_with_mqa.scales": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_b_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.kv_b_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_a_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_b_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.30.self_attn.q_b_proj.scales": "model-00031-of-00048.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.0.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.1.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.10.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.11.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.12.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.13.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.14.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.15.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.16.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.17.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.18.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.19.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.2.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.20.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.21.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.22.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.23.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.24.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.25.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.26.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.27.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.28.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.29.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.3.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.30.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.31.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.32.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.33.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.34.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.35.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.36.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.37.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.38.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.39.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.4.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.40.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.41.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.42.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.43.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.44.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.45.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.46.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.47.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.48.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.49.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.5.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.50.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.51.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.52.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.53.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.54.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.55.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.56.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.57.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.58.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.59.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.6.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.60.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.61.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.62.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.63.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.7.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.8.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.experts.9.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_a_proj_with_mqa.scales": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_b_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.kv_b_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_a_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_b_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.31.self_attn.q_b_proj.scales": "model-00032-of-00048.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.0.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.1.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.10.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.11.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.12.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.13.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.14.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.15.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.16.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.17.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.18.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.19.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.2.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.20.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.21.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.22.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.23.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.24.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.25.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.26.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.27.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.28.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.29.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.3.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.30.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.31.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.32.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.33.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.34.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.35.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.36.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.37.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.38.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.39.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.4.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.40.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.41.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.42.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.43.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.44.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.45.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.46.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.47.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.48.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.49.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.5.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.50.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.51.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.52.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.53.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.54.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.55.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.56.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.57.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.58.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.59.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.6.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.60.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.61.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.62.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.63.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.7.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.8.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.experts.9.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_a_proj_with_mqa.scales": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_b_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.kv_b_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_a_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_b_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.32.self_attn.q_b_proj.scales": "model-00033-of-00048.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.0.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.1.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.10.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.11.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.12.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.13.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.14.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.15.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.16.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.17.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.18.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.19.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.2.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.20.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.21.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.22.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.23.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.24.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.25.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.26.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.27.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.28.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.29.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.3.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.30.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.31.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.32.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.33.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.34.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.35.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.36.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.37.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.38.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.39.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.4.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.40.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.41.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.42.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.43.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.44.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.45.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.46.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.47.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.48.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.49.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.5.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.50.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.51.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.52.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.53.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.54.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.55.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.56.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.57.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.58.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.59.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.6.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.60.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.61.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.62.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.63.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.7.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.8.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.experts.9.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_a_proj_with_mqa.scales": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_b_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.kv_b_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_a_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_b_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.33.self_attn.q_b_proj.scales": "model-00034-of-00048.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.0.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.1.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.10.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.11.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.12.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.13.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.14.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.15.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.16.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.17.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.18.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.19.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.2.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.20.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.21.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.22.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.23.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.24.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.25.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.26.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.27.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.28.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.29.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.3.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.30.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.31.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.32.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.33.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.34.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.35.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.36.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.37.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.38.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.39.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.4.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.40.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.41.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.42.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.43.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.44.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.45.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.46.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.47.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.48.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.49.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.5.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.50.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.51.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.52.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.53.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.54.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.55.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.56.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.57.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.58.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.59.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.6.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.60.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.61.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.62.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.63.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.7.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.8.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.experts.9.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_a_proj_with_mqa.scales": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_b_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.kv_b_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_a_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_b_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.34.self_attn.q_b_proj.scales": "model-00035-of-00048.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.0.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.1.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.10.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.11.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.12.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.13.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.14.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.15.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.16.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.17.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.18.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.19.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.2.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.20.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.21.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.22.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.23.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.24.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.25.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.26.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.27.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.28.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.29.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.3.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.30.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.31.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.32.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.33.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.34.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.35.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.36.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.37.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.38.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.39.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.4.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.40.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.41.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.42.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.43.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.44.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.45.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.46.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.47.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.48.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.49.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.5.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.50.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.51.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.52.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.53.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.54.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.55.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.56.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.57.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.58.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.59.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.6.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.60.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.61.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.62.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.63.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.7.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.8.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.experts.9.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_a_proj_with_mqa.scales": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_b_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.kv_b_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_a_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_b_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.35.self_attn.q_b_proj.scales": "model-00036-of-00048.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.0.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.1.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.10.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.11.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.12.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.13.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.14.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.15.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.16.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.17.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.18.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.19.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.2.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.20.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.21.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.22.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.23.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.24.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.25.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.26.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.27.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.28.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.29.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.3.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.30.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.31.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.32.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.33.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.34.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.35.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.36.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.37.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.38.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.39.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.4.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.40.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.41.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.42.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.43.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.44.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.45.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.46.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.47.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.48.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.49.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.5.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.50.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.51.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.52.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.53.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.54.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.55.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.56.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.57.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.58.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.59.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.6.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.60.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.61.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.62.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.63.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.7.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.8.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.experts.9.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_a_proj_with_mqa.scales": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_b_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.kv_b_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_a_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_b_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.36.self_attn.q_b_proj.scales": "model-00037-of-00048.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.0.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.1.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.10.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.11.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.12.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.13.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.14.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.15.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.16.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.17.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.18.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.19.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.2.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.20.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.21.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.22.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.23.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.24.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.25.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.26.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.27.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.28.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.29.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.3.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.30.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.31.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.32.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.33.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.34.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.35.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.36.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.37.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.38.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.39.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.4.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.40.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.41.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.42.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.43.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.44.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.45.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.46.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.47.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.48.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.49.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.5.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.50.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.51.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.52.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.53.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.54.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.55.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.56.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.57.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.58.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.59.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.6.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.60.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.61.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.62.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.63.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.7.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.8.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.experts.9.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_a_proj_with_mqa.scales": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_b_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.kv_b_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_a_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_b_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.37.self_attn.q_b_proj.scales": "model-00038-of-00048.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.0.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.1.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.10.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.11.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.12.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.13.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.14.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.15.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.16.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.17.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.18.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.19.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.2.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.20.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.21.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.22.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.23.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.24.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.25.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.26.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.27.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.28.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.29.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.3.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.30.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.31.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.32.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.33.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.34.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.35.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.36.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.37.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.38.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.39.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.4.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.40.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.41.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.42.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.43.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.44.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.45.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.46.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.47.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.48.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.49.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.5.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.50.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.51.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.52.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.53.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.54.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.55.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.56.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.57.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.58.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.59.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.6.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.60.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.61.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.62.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.63.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.7.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.8.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.experts.9.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_a_proj_with_mqa.scales": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_b_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.kv_b_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_a_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_b_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.38.self_attn.q_b_proj.scales": "model-00039-of-00048.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.0.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.1.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.10.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.11.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.12.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.13.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.14.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.15.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.16.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.17.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.18.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.19.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.2.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.20.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.21.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.22.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.23.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.24.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.25.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.26.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.27.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.28.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.29.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.3.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.30.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.31.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.32.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.33.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.34.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.35.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.36.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.37.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.38.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.39.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.4.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.40.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.41.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.42.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.43.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.44.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.45.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.46.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.47.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.48.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.49.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.5.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.50.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.51.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.52.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.53.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.54.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.55.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.56.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.57.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.58.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.59.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.6.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.60.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.61.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.62.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.63.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.7.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.8.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.experts.9.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_a_proj_with_mqa.scales": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_b_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.kv_b_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_a_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_b_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.39.self_attn.q_b_proj.scales": "model-00040-of-00048.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.0.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.1.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.10.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.11.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.12.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.13.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.14.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.15.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.16.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.17.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.18.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.19.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.2.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.20.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.21.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.22.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.23.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.24.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.25.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.26.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.27.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.28.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.29.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.3.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.30.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.31.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.32.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.33.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.34.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.35.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.36.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.37.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.38.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.39.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.4.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.40.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.41.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.42.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.43.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.44.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.45.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.46.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.47.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.48.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.49.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.5.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.50.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.51.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.52.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.53.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.54.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.55.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.56.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.57.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.58.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.59.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.6.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.60.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.61.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.62.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.63.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.7.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.8.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.experts.9.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_a_proj_with_mqa.scales": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_b_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.kv_b_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_a_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_b_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.40.self_attn.q_b_proj.scales": "model-00041-of-00048.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.0.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.1.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.10.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.11.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.12.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.13.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.14.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.15.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.16.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.17.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.18.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.19.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.2.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.20.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.21.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.22.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.23.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.24.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.25.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.26.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.27.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.28.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.29.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.3.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.30.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.31.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.32.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.33.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.34.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.35.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.36.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.37.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.38.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.39.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.4.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.40.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.41.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.42.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.43.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.44.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.45.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.46.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.47.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.48.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.49.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.5.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.50.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.51.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.52.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.53.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.54.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.55.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.56.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.57.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.58.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.59.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.6.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.60.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.61.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.62.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.63.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.7.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.8.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.experts.9.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_a_proj_with_mqa.scales": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_b_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.kv_b_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_a_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_b_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.41.self_attn.q_b_proj.scales": "model-00042-of-00048.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.0.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.1.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.10.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.11.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.12.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.13.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.14.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.15.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.16.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.17.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.18.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.19.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.2.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.20.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.21.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.22.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.23.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.24.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.25.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.26.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.27.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.28.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.29.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.3.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.30.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.31.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.32.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.33.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.34.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.35.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.36.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.37.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.38.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.39.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.4.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.40.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.41.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.42.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.43.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.44.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.45.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.46.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.47.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.48.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.49.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.5.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.50.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.51.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.52.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.53.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.54.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.55.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.56.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.57.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.58.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.59.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.6.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.60.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.61.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.62.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.63.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.7.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.8.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.experts.9.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_a_proj_with_mqa.scales": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_b_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.kv_b_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_a_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_b_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.42.self_attn.q_b_proj.scales": "model-00043-of-00048.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.0.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.1.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.10.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.11.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.12.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.13.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.14.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.15.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.16.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.17.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.18.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.19.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.2.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.20.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.21.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.22.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.23.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.24.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.25.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.26.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.27.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.28.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.29.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.3.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.30.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.31.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.32.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.33.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.34.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.35.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.36.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.37.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.38.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.39.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.4.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.40.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.41.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.42.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.43.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.44.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.45.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.46.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.47.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.48.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.49.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.5.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.50.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.51.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.52.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.53.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.54.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.55.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.56.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.57.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.58.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.59.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.6.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.60.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.61.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.62.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.63.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.7.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.8.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.experts.9.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_a_proj_with_mqa.scales": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_b_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.kv_b_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_a_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_b_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.43.self_attn.q_b_proj.scales": "model-00044-of-00048.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.0.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.1.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.10.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.11.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.12.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.13.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.14.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.15.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.16.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.17.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.18.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.19.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.2.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.20.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.21.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.22.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.23.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.24.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.25.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.26.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.27.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.28.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.29.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.3.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.30.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.31.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.32.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.33.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.34.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.35.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.36.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.37.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.38.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.39.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.4.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.40.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.41.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.42.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.43.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.44.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.45.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.46.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.47.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.48.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.49.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.5.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.50.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.51.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.52.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.53.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.54.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.55.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.56.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.57.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.58.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.59.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.6.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.60.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.61.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.62.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.63.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.7.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.8.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.experts.9.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_a_proj_with_mqa.scales": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_b_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.kv_b_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_a_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_b_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.44.self_attn.q_b_proj.scales": "model-00045-of-00048.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.0.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.1.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.10.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.11.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.12.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.13.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.14.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.15.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.16.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.17.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.18.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.19.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.2.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.20.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.21.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.22.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.23.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.24.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.25.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.26.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.27.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.28.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.29.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.3.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.30.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.31.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.32.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.33.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.34.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.35.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.36.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.37.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.38.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.39.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.4.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.40.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.41.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.42.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.43.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.44.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.45.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.46.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.47.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.48.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.49.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.5.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.50.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.51.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.52.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.53.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.54.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.55.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.56.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.57.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.58.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.59.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.6.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.60.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.61.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.62.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.63.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.7.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.8.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.experts.9.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_a_proj_with_mqa.scales": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_b_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.kv_b_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_a_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_b_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.45.self_attn.q_b_proj.scales": "model-00046-of-00048.safetensors", + "model.layers.46.input_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.0.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.1.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.10.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.11.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.12.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.13.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.14.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.15.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.16.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.17.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.18.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.19.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.2.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.20.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.21.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.22.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.23.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.24.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.25.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.26.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.27.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.28.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.29.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.3.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.30.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.31.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.32.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.33.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.34.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.35.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.36.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.37.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.38.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.39.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.4.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.40.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.41.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.42.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.43.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.44.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.45.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.46.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.47.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.48.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.49.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.5.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.50.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.51.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.52.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.53.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.54.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.55.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.56.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.57.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.58.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.59.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.6.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.60.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.61.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.62.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.63.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.7.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.8.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.experts.9.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_a_proj_with_mqa.scales": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_b_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.kv_b_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_a_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_b_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.46.self_attn.q_b_proj.scales": "model-00047-of-00048.safetensors", + "model.layers.47.embed_tokens.weight": "model-00048-of-00048.safetensors", + "model.layers.47.embed_tokens.scales": "model-00048-of-00048.safetensors", + "lm_head.weight": "model-00048-of-00048.safetensors", + "model.embed_tokens.weight": "model-00048-of-00048.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..aba40197a4cdb5607f4ab7a05fb0a4ee8054fd6d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d +size 20217442 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f6d3074564f6dd3a9431bd43b968cef999d58c54 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,321 @@ +{ + "added_tokens_decoder": { + "154820": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154821": { + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154822": { + "content": "[gMASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154823": { + "content": "[sMASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154824": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154825": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154826": { + "content": "<|system|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154827": { + "content": "<|user|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154828": { + "content": "<|assistant|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154829": { + "content": "<|observation|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154830": { + "content": "<|begin_of_image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154831": { + "content": "<|end_of_image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154832": { + "content": "<|begin_of_video|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154833": { + "content": "<|end_of_video|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154834": { + "content": "<|begin_of_audio|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154835": { + "content": "<|end_of_audio|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154836": { + "content": "<|begin_of_transcription|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154837": { + "content": "<|end_of_transcription|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "154838": { + "content": "<|code_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154839": { + "content": "<|code_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154840": { + "content": "<|code_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154841": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154842": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154843": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154844": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154845": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154846": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154847": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154848": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154849": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154850": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154851": { + "content": "/nothink", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154852": { + "content": "<|begin_of_box|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154853": { + "content": "<|end_of_box|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154854": { + "content": "<|image|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "154855": { + "content": "<|video|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": 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|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>" + ], + "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" +}