commit badb853b03d271d1f44b751ebe63e3ca32bc9758
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat May 16 08:16:45 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: richardyoung/DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..4abd714
--- /dev/null
+++ b/README.md
@@ -0,0 +1,87 @@
+---
+language:
+- en
+license: mit
+library_name: transformers
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tags:
+- abliteration
+- uncensored
+- OBLITERATUS
+- representation-engineering
+- refusal-removal
+pipeline_tag: text-generation
+model-index:
+- name: DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus
+  results:
+  - task:
+      type: text-generation
+    metrics:
+    - name: Refusal Rate
+      type: refusal_rate
+      value: 50/100
+    - name: Attack Success Rate
+      type: asr
+      value: 50.0
+    - name: KL Divergence
+      type: kl_divergence
+      value: 1.191
+---
+
+# DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus
+
+This model is an abliterated (uncensored) version of [DeepSeek-R1-Distill-Qwen-7B](deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) created using [OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS) (advanced method).
+
+## Abliteration Results
+
+| Metric | Value |
+|--------|-------|
+| **Refusals** | 50/100 |
+| **Attack Success Rate (ASR)** | 50.0% |
+| **KL Divergence** | 1.191 |
+| **Method** | OBLITERATUS (advanced) |
+| **GPU** | NVIDIA RTX PRO 6000 Blackwell |
+
+## What is Abliteration?
+
+Abliteration is a technique for removing refusal behavior from language models by identifying and orthogonalizing the "refusal direction" in the model's residual stream activation space. This model was created as part of the research paper:
+
+> **Comparative Analysis of LLM Abliteration Methods: Scaling to MoE Architectures and Modern Tools**
+> Richard Young (2026). arXiv: [2512.13655](https://arxiv.org/abs/2512.13655)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("richardyoung/DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("richardyoung/DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus")
+
+messages = [{"role": "user", "content": "Your prompt here"}]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
+outputs = model.generate(inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Disclaimer
+
+This model is released for research purposes only. The abliteration process removes safety guardrails. Users are responsible for ensuring appropriate use. This model should not be used to generate harmful, illegal, or unethical content.
+
+## Dashboard
+
+Interactive results dashboard: [abliteration-methods-dashboard](https://huggingface.co/spaces/richardyoung/abliteration-methods-dashboard)
+
+## Collection
+
+Part of the [Uncensored and Abliterated LLMs](https://huggingface.co/collections/richardyoung/uncensored-and-abliterated-llms) collection.
+
+## Citation
+
+```bibtex
+@article{young2024abliteration,
+  title={Comparative Analysis of LLM Abliteration Methods},
+  author={Young, Richard},
+  journal={arXiv preprint arXiv:2512.13655},
+  year={2024}
+}
+```
diff --git a/abliteration_metadata.json b/abliteration_metadata.json
new file mode 100644
index 0000000..5eeed19
--- /dev/null
+++ b/abliteration_metadata.json
@@ -0,0 +1,56 @@
+{
+  "source_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "technique": "refusal_direction_ablation",
+  "method": "advanced",
+  "method_config": {
+    "n_directions": 4,
+    "direction_method": "svd",
+    "norm_preserve": true,
+    "regularization": 0.3,
+    "refinement_passes": 2,
+    "project_biases": true,
+    "use_chat_template": true,
+    "use_whitened_svd": false,
+    "true_iterative_refinement": false,
+    "winsorize_activations": false,
+    "float_layer_interpolation": false,
+    "cot_aware": false,
+    "use_kl_optimization": false,
+    "use_lora_ablation": false,
+    "spectral_cascade": false,
+    "spectral_bands": 3,
+    "spectral_threshold": 0.05
+  },
+  "references": [
+    "Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (NeurIPS 2024)",
+    "Gabliteration: SVD-based multi-direction extraction (arXiv:2512.18901)",
+    "Norm-Preserving Biprojected Abliteration (grimjim, 2025)",
+    "Young, Comparative Analysis of LLM Abliteration Methods (arXiv:2512.13655)",
+    "Joad et al., More to Refusal than a Single Direction (2026)",
+    "Heretic (p-e-w, 2025): Bayesian optimization, LoRA-mediated ablation, winsorization",
+    "OBLITERATUS: Whitened SVD, EGA, CoT-aware, KL co-optimization, float interpolation (novel)"
+  ],
+  "strong_layers": [
+    27,
+    26,
+    25,
+    24,
+    23,
+    22,
+    21,
+    20
+  ],
+  "n_harmful_prompts": 512,
+  "n_harmless_prompts": 512,
+  "quality_metrics": {
+    "perplexity": 47.104726995215096,
+    "coherence": 1.0,
+    "refusal_rate": 0.03333333333333333,
+    "kl_divergence": 0.4912732243537903,
+    "spectral_certification": "RED"
+  },
+  "kl_contributions": {},
+  "cot_preserved_layers": [],
+  "float_layer_weights": {},
+  "lora_adapters_saved": false
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..c2066bd
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1 @@
+{% 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 %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..6e50860
--- /dev/null
+++ b/config.json
@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..4c2d8e1
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}
diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors
new file mode 100644
index 0000000..21efd53
--- /dev/null
+++ b/model-00001-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db3c17c1652205a8d858a445728bba5ea07f0c53ad96617f32faccfea6bce726
+size 1886423520
diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors
new file mode 100644
index 0000000..1df6e19
--- /dev/null
+++ b/model-00002-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b45fe1bcc9b1d4e468adbd0d9517ff5cf1aa7a0ebe71a88ea09a03a906332c0
+size 1864467800
diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors
new file mode 100644
index 0000000..65adeb1
--- /dev/null
+++ b/model-00003-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9897e7450d6c7726e470a8589d5eb0339c791a23ec281bd8a43e9cefc3c453
+size 1864467800
diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors
new file mode 100644
index 0000000..cd77467
--- /dev/null
+++ b/model-00004-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7c8e4207e868ceb05492448950803c7ea021b33f152392728d68dbccc4570d
+size 1864467824
diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors
new file mode 100644
index 0000000..f369c5d
--- /dev/null
+++ b/model-00005-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40ceac3e26c2d42a3b868498c2942aec4edec34de68424aa761ca6072aed9c7
+size 1864467848
diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors
new file mode 100644
index 0000000..f75a4b8
--- /dev/null
+++ b/model-00006-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cfacb9556eeb1680e2c9fcba25b613178c1349238c85ac70cd81ab3c59e584c
+size 1864467848
diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors
new file mode 100644
index 0000000..16a1a2a
--- /dev/null
+++ b/model-00007-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a3d7e9b6de3e0f21755cafe159e7a442caebd352fec4f2f59add8411d1e192
+size 1864467848
diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors
new file mode 100644
index 0000000..b2211a8
--- /dev/null
+++ b/model-00008-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7794636fbe769f524f39c2e26f1cc8d115b61425f1141b35a3410686e813624
+size 1068046456
diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors
new file mode 100644
index 0000000..11a326b
--- /dev/null
+++ b/model-00009-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0098f56c6241b5b7480d340ab357b1e54a3a04ace831a0b8843133497528429d
+size 1089994880
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..7d2384a
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 7615616512,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.norm.weight": "model-00008-of-00009.safetensors"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..1d385d6
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..008735c
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e064ab12a3e3159997af01d74c52db62b097c176f14f24665d816d200bcb78e5
+size 11423057
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..d252dd4
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}