初始化项目，由ModelHub XC社区提供模型

Model: allenai/BAR-2x7B-Safety
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,45 @@
+---
+license: apache-2.0
+library_name: transformers
+tags:
+  - bar
+  - mixture-of-experts
+  - olmo
+---
+
+# BAR
+
+BAR (Branch-Adapt-Route) is a modular post-training approach that extends a fully post-trained language model with new domain capabilities via independently trained Mixture-of-Experts. Rather than retraining a single model across all domains, BAR trains independent domain experts — each through its own mid-training, supervised finetuning (SFT), and reinforcement learning pipeline — and composes them into a unified model via an MoE architecture with lightweight router training.
+
+All BAR models are built on top of Olmo 2 7B.
+
+## Models in the BAR suite
+
+- **BAR-7B** — initial fully post-trained 7B dense model (the starting point)
+- **BAR-2x7B-Base** — 2-expert MoE (anchor + base pre-trained model)
+- **BAR-2x7B-Math-SFT** — math expert after mid-training and SFT
+- **BAR-2x7B-Math** — math expert after mid-training + SFT + RLVR
+- **BAR-2x7B-Code-SFT** — code expert after mid-training and SFT
+- **BAR-2x7B-Code** — code expert after mid-training + SFT + RLVR
+- **BAR-2x7B-Tool-Use** — tool use expert (SFT only)
+- **BAR-2x7B-Safety** — safety expert (SFT only)
+- **BAR-5x7B** — final 5-expert MoE combining all experts with a trained router
+
+## Results
+
+| Model | Overall | Knowledge | Reasoning | Chat | Math | Code | Tool Use | Safety |
+|---|---|---|---|---|---|---|---|---|
+| BAR-7B            | 31.3 | 28.5 | 29.8 | 48.9 | 23.6 | 11.8 | 25.3 | 51.3 |
+| BAR-2x7B-Math-SFT | 36.8 | 28.8 | 31.2 | 40.9 | 41.9 | 20.5 | 21.6 | 72.7 |
+| BAR-2x7B-Math     | 39.3 | 29.0 | 30.8 | 42.5 | 55.8 | 22.1 | 19.8 | 75.4 |
+| BAR-2x7B-Code-SFT | 38.5 | 28.8 | 29.1 | 40.1 | 25.5 | 49.3 | 19.7 | 77.3 |
+| BAR-2x7B-Code     | 38.8 | 28.5 | 29.2 | 41.0 | 26.9 | 50.4 | 19.8 | 75.3 |
+| BAR-2x7B-Tool-Use | 37.2 | 28.5 | 28.7 | 39.3 | 21.8 | 16.9 | 46.4 | 79.1 |
+| BAR-2x7B-Safety   | 35.6 | 28.7 | 28.8 | 38.1 | 22.4 | 15.7 | 21.1 | 94.6 |
+| BAR-5x7B          | 49.1 | 28.4 | 30.8 | 38.7 | 56.2 | 49.9 | 45.6 | 94.0 |
+
+Scores are unweighted averages across benchmarks within each category. See the paper for per-benchmark results and full evaluation details.
+
+## License
+
+This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's [Responsible Use Guidelines](https://allenai.org/responsible-use).

chat_template.jinja

@@ -0,0 +1,16 @@
+{% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system
+You are OLMo, a helpful function-calling AI assistant built by Ai2. Your date cutoff is November 2024, and your model weights are available at https://huggingface.co/allenai. You do not currently have access to any functions. <functions></functions><|im_end|>
+' }}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system
+' + message['content'] }}{% if message.get('functions', none) is not none %}{{ ' <functions>' + message['functions'] + '</functions><|im_end|>
+' }}{% else %}{{ ' You do not currently have access to any functions. <functions></functions><|im_end|>
+' }}{% endif %}{% elif message['role'] == 'user' %}{% if message.get('functions', none) is not none %}{{ '<|im_start|>user
+' + message['content'] + '
+' + '<functions>' + message['functions'] + '</functions><|im_end|>
+' }}{% else %}{{ '<|im_start|>user
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant
+' }}{% if message.get('content', none) is not none %}{{ message['content'] }}{% endif %}{% if message.get('function_calls', none) is not none %}{{ '<function_calls>' + message['function_calls'] + '</function_calls>' }}{% endif %}{% if not loop.last %}{{ '<|im_end|>' + '
+' }}{% else %}{{ eos_token }}{% endif %}{% elif message['role'] == 'environment' %}{{ '<|im_start|>environment
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "FlexOlmoForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 65536,
+  "model_type": "flex_olmo",
+  "norm_topk_prob": false,
+  "num_attention_heads": 32,
+  "num_experts": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "output_router_logits": false,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "router_aux_loss_coef": 0.01,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 100278
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    100265,
+    100257
+  ],
+  "pad_token": 100277,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cc8b4310a0af0687e37472ee1046d31937c131ba645738e88b79967b1aa068
+size 4974144448

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e275ef46829267ea85245dfd9c7e7d1e290b433cbb89b57ab4adbb423194a71a
+size 4941280192

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b695f4168de7f3940ac8bd0ee4befebc9aad3f17ee87253eddda550c335a5b
+size 4997870256

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e1e9e63a7560dbd8e640227a87ab1693ff30c8f6a7d3d3fdf7f8194c6ae61f
+size 4951782856

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84878d476f4911fc9c1e767461f75b9d71616d19f926567c74584069912e538
+size 3388570072

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_parameters": 11626795008,
+    "total_size": 23253590016
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.experts.1.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.mlp.experts.0.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.experts.0.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.experts.1.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.experts.0.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.experts.0.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.experts.1.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.experts.1.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.experts.0.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.experts.0.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.experts.1.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.experts.1.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.gate.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.experts.0.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.experts.0.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.experts.1.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.experts.1.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.gate.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.mlp.experts.0.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.experts.0.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.experts.1.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.experts.1.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.gate.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.experts.0.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.experts.0.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.experts.1.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.experts.1.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.gate.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.experts.0.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.experts.0.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.experts.1.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.experts.1.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.experts.0.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.experts.0.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.experts.1.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.experts.1.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<functions>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "</functions>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<function_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "</function_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 65536,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}