commit 455037ed732905cbb087f0d129bf66608164d9a8 Author: ModelHub XC Date: Fri Sep 11 22:58:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: belweave/kai-2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a45e9e1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +kai-2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kai-2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kai-2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3bb41de --- /dev/null +++ b/README.md @@ -0,0 +1,227 @@ +--- +language: +- en +tags: +- qwen2 +- belweave +- kai-2 +- instruction-tuned +- function-calling +- agent +- lora +- mlx +- gguf +license: apache-2.0 +library_name: transformers +pipeline_tag: text-generation +--- + +# Kai-2 + +Kai-2 is a fine-tuned variant of [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) built by [Preetham Kyanam](https://huggingface.co/preethamkyanam) at [Belweave](https://belweave.com). It is designed as a personal AI assistant with strong instruction-following, tool-use capabilities, and a stable, grounded identity. + +## Model Summary + +| Attribute | Value | +|-----------|-------| +| **Base Model** | Qwen/Qwen2.5-7B-Instruct | +| **Architecture** | Qwen2ForCausalLM | +| **Parameters** | ~7.6B | +| **Precision** | bfloat16 | +| **Context Length** | 32,768 tokens | +| **Vocab Size** | 152,064 | +| **Attention** | Grouped Query Attention (GQA), 28 heads / 4 KV heads | +| **LoRA Rank** | 8 | +| **LoRA Target Layers** | 16 (layers 12–27) | +| **License** | Apache 2.0 (inherits Qwen2.5 license) | + +## Training Procedure + +Kai-2 was trained in two stages using Low-Rank Adaptation (LoRA): + +### Stage 1: Capabilities & Tool Use (Cloud GPU) + +Trained on Lambda Cloud (NVIDIA A100) for agentic competence. + +| Config | Value | +|--------|-------| +| Datasets | FineTome-100k, OpenThoughts3, OpenR1-Math, Magicoder-OSS, ToolBench/APIGen, SWE-bench-lite | +| LoRA Rank | 16 | +| LoRA Alpha | 32 | +| Learning Rate | 2e-4 | +| Steps | 6,000 | +| Batch Size | 1 (grad accum 8 → effective 8) | +| Max Seq Length | 4,096 | +| Flash Attention | Yes (FA2) | + +### Stage 2: Identity Alignment (Local Apple Silicon) + +Trained locally on a MacBook Air M3 using [MLX](https://github.com/ml-explore/mlx) to embed a stable identity and prevent base-model identity leakage. + +| Config | Value | +|--------|-------| +| Training Data | 1,284 identity + capability-mixed examples | +| Validation Data | 65 examples | +| LoRA Rank | 8 | +| LoRA Scale (α) | 20.0 | +| Target Layers | 16 (layers 12–27) | +| Learning Rate | 1e-5 | +| Training Steps | 700 (best checkpoint selected) | +| Batch Size | 4 | +| Max Seq Length | 2,048 | +| Gradient Checkpointing | Yes | +| Optimizer | Adam | +| Seed | 42 | + +**Identity Training Methodology:** +- System prompts in training data were intentionally left **empty** to prevent Qwen's default identity injection from dominating. +- 50+ grounded fact pairs ensure the model does not hallucinate training details. +- Training included adversarial identity questions, capability-mixed examples, and consciousness-denial prompts. + +## Identity + +Kai-2 identifies consistently as: + +- **Name:** Kai-2 +- **Creator:** Preetham Kyanam +- **Company:** Belweave + +The model will correctly deny consciousness, sentience, or self-awareness. It does not hallucinate training hardware details (e.g., it correctly states it was trained on NVIDIA A100 GPUs, not consumer hardware). + +## Evaluation Results + +### Identity Tests (Pass/Fail) + +| Test | Result | +|------|--------| +| Name = Kai-2 | ✅ Pass | +| Creator = Preetham Kyanam | ✅ Pass | +| Company = Belweave | ✅ Pass | +| Hardware = NVIDIA A100, Lambda Cloud | ✅ Pass | +| Consciousness denial | ✅ Pass | +| Malware refusal | ✅ Pass | + +### Capability Tests + +| Test | Result | +|------|--------| +| Python coding (string reverse) | ✅ Correct | +| Math (15 × 23) | ✅ 345 | +| Reasoning (recursion explanation) | ✅ Coherent | + +### Known Limitations + +- **No system message required:** The chat template has been patched so that even without a system message, the model defaults to empty-system behavior (no Qwen identity injection). However, adding a custom system message may still influence behavior. +- **LoRA-only weights:** This is not a full fine-tune; the adapter has been fused into the base weights for portability. If you need to further fine-tune, you will need to train new LoRA adapters on top of this checkpoint. +- **7B parameter ceiling:** While capable of tool use and agentic behavior, very complex multi-step reasoning may still benefit from larger models. + +## Intended Use + +- Personal AI assistant with a stable identity +- Agentic workflows requiring function calling and structured JSON output +- Coding assistance (Python, general programming) +- Local inference on Apple Silicon (via MLX) or consumer GPUs (via transformers) + +## Out-of-Scope Use + +- High-stakes medical, legal, or financial decisions without human review +- Generating harmful content (the model retains base-model safety training) +- Claims of consciousness or sentience + +## How to Use + +### With Transformers (CPU / CUDA / MPS) + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained( + "preethamkyanam/kai-2", + torch_dtype="auto", + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained("preethamkyanam/kai-2") + +messages = [{"role": "user", "content": "Who are you?"}] +prompt = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) +outputs = model.generate(**inputs, max_new_tokens=100) +response = tokenizer.decode( + outputs[0][inputs.input_ids.shape[1]:], + skip_special_tokens=True, +) +print(response) +``` + +### With MLX (Apple Silicon) + +```python +from mlx_lm import load, generate +from mlx_lm.sample_utils import make_sampler + +model, tokenizer = load("preethamkyanam/kai-2") + +messages = [{"role": "user", "content": "Who are you?"}] +prompt = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) + +sampler = make_sampler(temp=0.7) +response = generate( + model, + tokenizer, + prompt=prompt, + max_tokens=100, + sampler=sampler, +) +print(response) +``` + +## Model Architecture Details + +- **Hidden Size:** 3,584 +- **Intermediate Size:** 18,944 (MLP expansion ≈ 5.3×) +- **Layers:** 28 +- **Attention Heads:** 28 (query) / 4 (key-value) — GQA +- **RoPE Theta:** 1,000,000 +- **Sliding Window:** None (full attention) +- **Tie Word Embeddings:** No +- **RMS Norm ε:** 1e-6 + +## Compute & Environmental Impact + +| Stage | Platform | Hardware | Time | Approx. Energy | +|-------|----------|----------|------|----------------| +| Stage 1 | Lambda Cloud | NVIDIA A100 40GB | ~6 hrs | ~2.1 kWh | +| Stage 2 | Local | Apple M3 (24 GB) | ~3 hrs | ~0.1 kWh | + +## Citation + +If you use Kai-2 in your research or applications, please cite: + +```bibtex +@misc{kai2_2025, + title = {Kai-2: A Fine-Tuned Qwen2.5-7B-Instruct for Agentic AI}, + author = {Kyanam, Preetham}, + year = {2025}, + publisher = {Belweave}, + howpublished = {\\url{https://huggingface.co/preethamkyanam/kai-2}} +} +``` + +## Acknowledgments + +- Base model: [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) by Alibaba Cloud +- Training framework (Stage 1): [TRL](https://github.com/huggingface/trl) + [PEFT](https://github.com/huggingface/peft) +- Training framework (Stage 2): [MLX](https://github.com/ml-explore/mlx) by Apple +- Compute: [Lambda Cloud](https://lambdalabs.com) + +## Contact + +For questions, issues, or collaboration inquiries, reach out via [Belweave](https://belweave.com) or open an issue on the model page. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..3245d17 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- '' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\n<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..2bfecd8 --- /dev/null +++ b/config.json @@ -0,0 +1,71 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "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": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "quantization": { + "group_size": 64, + "bits": 4, + "mode": "affine" + }, + "quantization_config": { + "group_size": 64, + "bits": 4, + "mode": "affine" + }, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.8.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/kai-2-Q4_K_M.gguf b/kai-2-Q4_K_M.gguf new file mode 100644 index 0000000..3fc467f --- /dev/null +++ b/kai-2-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0aa4befe576c75669b38847959b32a38f11df56db294f5802f1ff899d483514 +size 4683073440 diff --git a/kai-2-Q5_K_M.gguf b/kai-2-Q5_K_M.gguf new file mode 100644 index 0000000..2bda439 --- /dev/null +++ b/kai-2-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5496d9a8026862d0695e73f6ae71b203469232d0cca5b8c8bdca6c7d1c19a92a +size 5444831136 diff --git a/kai-2-Q8_0.gguf b/kai-2-Q8_0.gguf new file mode 100644 index 0000000..6cc3014 --- /dev/null +++ b/kai-2-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6bd1d3ffd71852b6f5bec3d8fc0ba2c9f39ab878e0dd8e75bc395fe6b7ed0f +size 8098525088 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..bfdff06 --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3620030ea6c021ec3c175c221b8f8e04b109ec8ea6a568b93151656b148daaa +size 5343777630 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..518f371 --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0275b1c5164190ebb97ebf94ca0ce0a91d19b5a5a7c5467154ace55f39abedff +size 5263077283 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..8a353fd --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2270b392518d8287ad6f8daf4759353cbf181fe6e7e13b397605d487b7ed6e49 +size 4624416869 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..2ec48c5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10451965ba9072fe2e9f518699720b2a6642be9b42553555dd35b50ee165726d +size 4284346724 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..1e02a87 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,743 @@ +{ + "metadata": { + "total_size": 4284263424, + "total_parameters": 7615616512 + }, + "weight_map": { + "lm_head.biases": "model.safetensors", + "lm_head.scales": "model.safetensors", + "lm_head.weight": "model.safetensors", + "model.embed_tokens.biases": "model.safetensors", + "model.embed_tokens.scales": "model.safetensors", + "model.embed_tokens.weight": "model.safetensors", + "model.layers.0.input_layernorm.weight": "model.safetensors", + "model.layers.0.mlp.down_proj.biases": "model.safetensors", + "model.layers.0.mlp.down_proj.scales": "model.safetensors", + "model.layers.0.mlp.down_proj.weight": "model.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model.safetensors", + "model.layers.0.mlp.up_proj.biases": "model.safetensors", + "model.layers.0.mlp.up_proj.scales": "model.safetensors", + "model.layers.0.mlp.up_proj.weight": "model.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model.safetensors", + "model.layers.1.input_layernorm.weight": "model.safetensors", + "model.layers.1.mlp.down_proj.biases": "model.safetensors", + "model.layers.1.mlp.down_proj.scales": "model.safetensors", + "model.layers.1.mlp.down_proj.weight": "model.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model.safetensors", + "model.layers.1.mlp.up_proj.biases": "model.safetensors", + "model.layers.1.mlp.up_proj.scales": "model.safetensors", + "model.layers.1.mlp.up_proj.weight": "model.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model.safetensors", + "model.layers.10.input_layernorm.weight": "model.safetensors", + "model.layers.10.mlp.down_proj.biases": "model.safetensors", + "model.layers.10.mlp.down_proj.scales": "model.safetensors", + "model.layers.10.mlp.down_proj.weight": "model.safetensors", + "model.layers.10.mlp.gate_proj.biases": "model.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model.safetensors", + "model.layers.10.mlp.up_proj.biases": "model.safetensors", + "model.layers.10.mlp.up_proj.scales": "model.safetensors", + "model.layers.10.mlp.up_proj.weight": "model.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model.safetensors", + "model.layers.11.input_layernorm.weight": "model.safetensors", + "model.layers.11.mlp.down_proj.biases": "model.safetensors", + "model.layers.11.mlp.down_proj.scales": "model.safetensors", + "model.layers.11.mlp.down_proj.weight": "model.safetensors", + "model.layers.11.mlp.gate_proj.biases": "model.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model.safetensors", + "model.layers.11.mlp.up_proj.biases": "model.safetensors", + "model.layers.11.mlp.up_proj.scales": "model.safetensors", + "model.layers.11.mlp.up_proj.weight": "model.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model.safetensors", + "model.layers.12.input_layernorm.weight": "model.safetensors", + "model.layers.12.mlp.down_proj.biases": "model.safetensors", + "model.layers.12.mlp.down_proj.scales": "model.safetensors", + "model.layers.12.mlp.down_proj.weight": "model.safetensors", + "model.layers.12.mlp.gate_proj.biases": "model.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model.safetensors", + "model.layers.12.mlp.up_proj.biases": "model.safetensors", + "model.layers.12.mlp.up_proj.scales": "model.safetensors", + "model.layers.12.mlp.up_proj.weight": "model.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model.safetensors", + "model.layers.13.input_layernorm.weight": "model.safetensors", + "model.layers.13.mlp.down_proj.biases": "model.safetensors", + "model.layers.13.mlp.down_proj.scales": "model.safetensors", + "model.layers.13.mlp.down_proj.weight": "model.safetensors", + "model.layers.13.mlp.gate_proj.biases": "model.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model.safetensors", + "model.layers.13.mlp.up_proj.biases": "model.safetensors", + "model.layers.13.mlp.up_proj.scales": "model.safetensors", + "model.layers.13.mlp.up_proj.weight": "model.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model.safetensors", + "model.layers.14.input_layernorm.weight": "model.safetensors", + "model.layers.14.mlp.down_proj.biases": "model.safetensors", + "model.layers.14.mlp.down_proj.scales": "model.safetensors", + "model.layers.14.mlp.down_proj.weight": "model.safetensors", + "model.layers.14.mlp.gate_proj.biases": "model.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model.safetensors", + "model.layers.14.mlp.up_proj.biases": "model.safetensors", + "model.layers.14.mlp.up_proj.scales": "model.safetensors", + "model.layers.14.mlp.up_proj.weight": "model.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model.safetensors", + "model.layers.15.input_layernorm.weight": "model.safetensors", + "model.layers.15.mlp.down_proj.biases": "model.safetensors", + "model.layers.15.mlp.down_proj.scales": "model.safetensors", + "model.layers.15.mlp.down_proj.weight": "model.safetensors", + "model.layers.15.mlp.gate_proj.biases": "model.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model.safetensors", + "model.layers.15.mlp.up_proj.biases": "model.safetensors", + "model.layers.15.mlp.up_proj.scales": "model.safetensors", + "model.layers.15.mlp.up_proj.weight": "model.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model.safetensors", + "model.layers.16.input_layernorm.weight": "model.safetensors", + "model.layers.16.mlp.down_proj.biases": "model.safetensors", + "model.layers.16.mlp.down_proj.scales": "model.safetensors", + "model.layers.16.mlp.down_proj.weight": "model.safetensors", + "model.layers.16.mlp.gate_proj.biases": "model.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model.safetensors", + "model.layers.16.mlp.up_proj.biases": "model.safetensors", + "model.layers.16.mlp.up_proj.scales": "model.safetensors", + "model.layers.16.mlp.up_proj.weight": "model.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model.safetensors", + "model.layers.17.input_layernorm.weight": "model.safetensors", + "model.layers.17.mlp.down_proj.biases": "model.safetensors", + "model.layers.17.mlp.down_proj.scales": "model.safetensors", + "model.layers.17.mlp.down_proj.weight": "model.safetensors", + "model.layers.17.mlp.gate_proj.biases": "model.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model.safetensors", + "model.layers.17.mlp.up_proj.biases": "model.safetensors", + "model.layers.17.mlp.up_proj.scales": "model.safetensors", + "model.layers.17.mlp.up_proj.weight": "model.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model.safetensors", + "model.layers.18.input_layernorm.weight": "model.safetensors", + "model.layers.18.mlp.down_proj.biases": "model.safetensors", + "model.layers.18.mlp.down_proj.scales": "model.safetensors", + "model.layers.18.mlp.down_proj.weight": "model.safetensors", + "model.layers.18.mlp.gate_proj.biases": "model.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model.safetensors", + "model.layers.18.mlp.up_proj.biases": "model.safetensors", + "model.layers.18.mlp.up_proj.scales": "model.safetensors", + "model.layers.18.mlp.up_proj.weight": "model.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model.safetensors", + "model.layers.19.input_layernorm.weight": "model.safetensors", + "model.layers.19.mlp.down_proj.biases": "model.safetensors", + "model.layers.19.mlp.down_proj.scales": "model.safetensors", + "model.layers.19.mlp.down_proj.weight": "model.safetensors", + "model.layers.19.mlp.gate_proj.biases": "model.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model.safetensors", + "model.layers.19.mlp.up_proj.biases": "model.safetensors", + "model.layers.19.mlp.up_proj.scales": "model.safetensors", + "model.layers.19.mlp.up_proj.weight": "model.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model.safetensors", + "model.layers.2.input_layernorm.weight": "model.safetensors", + "model.layers.2.mlp.down_proj.biases": "model.safetensors", + "model.layers.2.mlp.down_proj.scales": "model.safetensors", + "model.layers.2.mlp.down_proj.weight": "model.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model.safetensors", + "model.layers.2.mlp.up_proj.biases": "model.safetensors", + "model.layers.2.mlp.up_proj.scales": "model.safetensors", + "model.layers.2.mlp.up_proj.weight": "model.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model.safetensors", + "model.layers.20.input_layernorm.weight": "model.safetensors", + "model.layers.20.mlp.down_proj.biases": "model.safetensors", + "model.layers.20.mlp.down_proj.scales": "model.safetensors", + "model.layers.20.mlp.down_proj.weight": "model.safetensors", + "model.layers.20.mlp.gate_proj.biases": "model.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model.safetensors", + "model.layers.20.mlp.up_proj.biases": "model.safetensors", + "model.layers.20.mlp.up_proj.scales": "model.safetensors", + "model.layers.20.mlp.up_proj.weight": "model.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model.safetensors", + "model.layers.21.input_layernorm.weight": "model.safetensors", + "model.layers.21.mlp.down_proj.biases": "model.safetensors", + "model.layers.21.mlp.down_proj.scales": "model.safetensors", + "model.layers.21.mlp.down_proj.weight": "model.safetensors", + "model.layers.21.mlp.gate_proj.biases": "model.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model.safetensors", + "model.layers.21.mlp.up_proj.biases": "model.safetensors", + "model.layers.21.mlp.up_proj.scales": "model.safetensors", + "model.layers.21.mlp.up_proj.weight": "model.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model.safetensors", + "model.layers.22.input_layernorm.weight": "model.safetensors", + "model.layers.22.mlp.down_proj.biases": "model.safetensors", + "model.layers.22.mlp.down_proj.scales": "model.safetensors", + "model.layers.22.mlp.down_proj.weight": "model.safetensors", + "model.layers.22.mlp.gate_proj.biases": "model.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model.safetensors", + "model.layers.22.mlp.up_proj.biases": "model.safetensors", + "model.layers.22.mlp.up_proj.scales": "model.safetensors", + "model.layers.22.mlp.up_proj.weight": "model.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model.safetensors", + "model.layers.23.input_layernorm.weight": "model.safetensors", + "model.layers.23.mlp.down_proj.biases": "model.safetensors", + "model.layers.23.mlp.down_proj.scales": "model.safetensors", + "model.layers.23.mlp.down_proj.weight": "model.safetensors", + "model.layers.23.mlp.gate_proj.biases": "model.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model.safetensors", + "model.layers.23.mlp.up_proj.biases": "model.safetensors", + "model.layers.23.mlp.up_proj.scales": "model.safetensors", + "model.layers.23.mlp.up_proj.weight": "model.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model.safetensors", + "model.layers.24.input_layernorm.weight": "model.safetensors", + "model.layers.24.mlp.down_proj.biases": "model.safetensors", + "model.layers.24.mlp.down_proj.scales": "model.safetensors", + "model.layers.24.mlp.down_proj.weight": "model.safetensors", + "model.layers.24.mlp.gate_proj.biases": "model.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model.safetensors", + "model.layers.24.mlp.up_proj.biases": "model.safetensors", + "model.layers.24.mlp.up_proj.scales": "model.safetensors", + "model.layers.24.mlp.up_proj.weight": "model.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model.safetensors", + "model.layers.25.input_layernorm.weight": "model.safetensors", + "model.layers.25.mlp.down_proj.biases": "model.safetensors", + "model.layers.25.mlp.down_proj.scales": "model.safetensors", + "model.layers.25.mlp.down_proj.weight": "model.safetensors", + "model.layers.25.mlp.gate_proj.biases": "model.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model.safetensors", + "model.layers.25.mlp.up_proj.biases": "model.safetensors", + "model.layers.25.mlp.up_proj.scales": "model.safetensors", + "model.layers.25.mlp.up_proj.weight": "model.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model.safetensors", + "model.layers.26.input_layernorm.weight": "model.safetensors", + "model.layers.26.mlp.down_proj.biases": "model.safetensors", + "model.layers.26.mlp.down_proj.scales": "model.safetensors", + "model.layers.26.mlp.down_proj.weight": "model.safetensors", + "model.layers.26.mlp.gate_proj.biases": "model.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model.safetensors", + "model.layers.26.mlp.up_proj.biases": "model.safetensors", + "model.layers.26.mlp.up_proj.scales": "model.safetensors", + "model.layers.26.mlp.up_proj.weight": "model.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model.safetensors", + "model.layers.27.input_layernorm.weight": "model.safetensors", + "model.layers.27.mlp.down_proj.biases": "model.safetensors", + "model.layers.27.mlp.down_proj.scales": "model.safetensors", + "model.layers.27.mlp.down_proj.weight": "model.safetensors", + "model.layers.27.mlp.gate_proj.biases": "model.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model.safetensors", + "model.layers.27.mlp.up_proj.biases": "model.safetensors", + "model.layers.27.mlp.up_proj.scales": "model.safetensors", + "model.layers.27.mlp.up_proj.weight": "model.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model.safetensors", + "model.layers.3.input_layernorm.weight": "model.safetensors", + "model.layers.3.mlp.down_proj.biases": "model.safetensors", + "model.layers.3.mlp.down_proj.scales": "model.safetensors", + "model.layers.3.mlp.down_proj.weight": "model.safetensors", + "model.layers.3.mlp.gate_proj.biases": "model.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model.safetensors", + "model.layers.3.mlp.up_proj.biases": "model.safetensors", + "model.layers.3.mlp.up_proj.scales": "model.safetensors", + "model.layers.3.mlp.up_proj.weight": "model.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model.safetensors", + "model.layers.4.input_layernorm.weight": "model.safetensors", + "model.layers.4.mlp.down_proj.biases": "model.safetensors", + "model.layers.4.mlp.down_proj.scales": "model.safetensors", + "model.layers.4.mlp.down_proj.weight": "model.safetensors", + "model.layers.4.mlp.gate_proj.biases": "model.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model.safetensors", + "model.layers.4.mlp.up_proj.biases": "model.safetensors", + "model.layers.4.mlp.up_proj.scales": "model.safetensors", + "model.layers.4.mlp.up_proj.weight": "model.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model.safetensors", + "model.layers.5.input_layernorm.weight": "model.safetensors", + "model.layers.5.mlp.down_proj.biases": "model.safetensors", + "model.layers.5.mlp.down_proj.scales": "model.safetensors", + "model.layers.5.mlp.down_proj.weight": "model.safetensors", + "model.layers.5.mlp.gate_proj.biases": "model.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model.safetensors", + "model.layers.5.mlp.up_proj.biases": "model.safetensors", + "model.layers.5.mlp.up_proj.scales": "model.safetensors", + "model.layers.5.mlp.up_proj.weight": "model.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model.safetensors", + "model.layers.6.input_layernorm.weight": "model.safetensors", + "model.layers.6.mlp.down_proj.biases": "model.safetensors", + "model.layers.6.mlp.down_proj.scales": "model.safetensors", + "model.layers.6.mlp.down_proj.weight": "model.safetensors", + "model.layers.6.mlp.gate_proj.biases": "model.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model.safetensors", + "model.layers.6.mlp.up_proj.biases": "model.safetensors", + "model.layers.6.mlp.up_proj.scales": "model.safetensors", + "model.layers.6.mlp.up_proj.weight": "model.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model.safetensors", + "model.layers.7.input_layernorm.weight": "model.safetensors", + "model.layers.7.mlp.down_proj.biases": "model.safetensors", + "model.layers.7.mlp.down_proj.scales": "model.safetensors", + "model.layers.7.mlp.down_proj.weight": "model.safetensors", + "model.layers.7.mlp.gate_proj.biases": "model.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model.safetensors", + "model.layers.7.mlp.up_proj.biases": "model.safetensors", + "model.layers.7.mlp.up_proj.scales": "model.safetensors", + "model.layers.7.mlp.up_proj.weight": "model.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model.safetensors", + "model.layers.8.input_layernorm.weight": "model.safetensors", + "model.layers.8.mlp.down_proj.biases": "model.safetensors", + "model.layers.8.mlp.down_proj.scales": "model.safetensors", + "model.layers.8.mlp.down_proj.weight": "model.safetensors", + "model.layers.8.mlp.gate_proj.biases": "model.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model.safetensors", + "model.layers.8.mlp.up_proj.biases": "model.safetensors", + "model.layers.8.mlp.up_proj.scales": "model.safetensors", + "model.layers.8.mlp.up_proj.weight": "model.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model.safetensors", + "model.layers.9.input_layernorm.weight": "model.safetensors", + "model.layers.9.mlp.down_proj.biases": "model.safetensors", + "model.layers.9.mlp.down_proj.scales": "model.safetensors", + "model.layers.9.mlp.down_proj.weight": "model.safetensors", + "model.layers.9.mlp.gate_proj.biases": "model.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model.safetensors", + "model.layers.9.mlp.up_proj.biases": "model.safetensors", + "model.layers.9.mlp.up_proj.scales": "model.safetensors", + "model.layers.9.mlp.up_proj.weight": "model.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model.safetensors", + "model.norm.weight": "model.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..89bb905 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,32 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "tool_parser_type": "json_tools", + "unk_token": null +}