初始化项目，由ModelHub XC社区提供模型

Model: ashoknimiwal/DeepSeek-R1-14B-Research-Snapshot
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+figures/benchmark.jpg filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 DeepSeek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,21 @@
+---
+language:
+  - en
+license: mit
+library_name: transformers
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+tags:
+  - research-reproducibility
+  - corporate-culture
+  - text-classification
+  - nlp
+  - earnings-calls
+  - deepseek
+  - qwen2.5
+  - reasoning
+pipeline_tag: text-generation
+---
+
+# DeepSeek-R1-Distill-Qwen-14B — Research Reproducibility Snapshot
+
+This repository hosts an exact, unmodified snapshot of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), preserved for research reproducibility. No weights, tokenizer files, or configurations have been altered. The snapshot was downloaded from the official DeepSeek repository on 29 April 2026 at commit [`1df8507`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/commit/1df8507178afcc1bef68cd8c393f61a886323761) and is uploaded here to ensure that future researchers can use the identical model artifact, even if the upstream repository is modified, versioned, or removed. This model card serves as a supplementary resource to the associated manuscript, currently under review at *Information Systems Frontiers*. Methodological details and results are omitted here to comply with the publication policies of the target journal and will be added upon acceptance, subject to the publisher's copyright terms.

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

figures/benchmark.jpg

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fa3297b31b53a21a283886d9f6d5759433e7523bd63b09d5ac43e9422dae97
+size 777314

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.39.3"
+}

model-00001-of-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a080ebff55b277c0e106f19e4496a88b9f5db4059ea0a6b8ea7d9bb3ad4d0ca
+size 8714116464

model-00002-of-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8bc983706e8db5b270c319be58762f53c6222e0c6cd785c6fd8fd33c2e783e8
+size 8667059663

model-00003-of-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557341a00d5c2a75c24e03961d0e716571517d39c70a040633180d9edcbfe285
+size 8667059711

model-00004-of-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba8a9c8251b8f6c6beef7325102665f22b17c1f52ef76eaaa938bfeab1bd18c
+size 3491898034

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-000004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-000004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00003-of-000004.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00004-of-000004.safetensors",
+    "model.norm.weight": "model-00004-of-000004.safetensors",
+    "lm_head.weight": "model-00004-of-000004.safetensors"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
+}