commit b2985c89fb501ec919d4bc98337898829d7cc7da Author: ModelHub XC Date: Sun Sep 13 17:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ermiaazarkhalili/FastContext-4B-SFT_base-SFT-Claude-Opus-Reasoning-Unsloth 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..fdc1ab0 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: + - microsoft/FastContext-1.0-4B-SFT +library_name: transformers +pipeline_tag: text-generation +tags: + - unsloth + - lora + - trl + - sft +--- + +# FastContext-4B-SFT_base-SFT-Claude-Opus-Reasoning-Unsloth + +A LoRA fine-tune of [`microsoft/FastContext-1.0-4B-SFT`](https://huggingface.co/microsoft/FastContext-1.0-4B-SFT), supervised fine-tuned on `ermiaazarkhalili/claude-reasoning-distillation` (private) (config `sft`). + +| | | +| --- | --- | +| **Base model** | [`microsoft/FastContext-1.0-4B-SFT`](https://huggingface.co/microsoft/FastContext-1.0-4B-SFT) | +| **Architecture** | `Qwen3ForCausalLM` | +| **Parameters** | 4.0B | +| **Training data** | `ermiaazarkhalili/claude-reasoning-distillation` (private) (config `sft`) | +| **Method** | LoRA supervised fine-tuning via [Unsloth](https://github.com/unslothai/unsloth) + [TRL](https://github.com/huggingface/trl) | + +## Usage + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "ermiaazarkhalili/FastContext-4B-SFT_base-SFT-Claude-Opus-Reasoning-Unsloth" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id, dtype='auto', device_map='auto') + +messages = [{"role": "user", "content": "Explain gradient checkpointing in two sentences."}] +inputs = tokenizer.apply_chat_template( + messages, add_generation_prompt=True, return_tensors='pt' +).to(model.device) + +outputs = model.generate(inputs, max_new_tokens=256) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Training configuration + +| Setting | Value | +| --- | --- | +| LoRA rank (r) | 16 | +| LoRA alpha | 16 | +| Learning rate | 0.0002 | +| Epochs | 1 | +| Effective batch size | 8 (2 x 4 grad accum) | +| Max sequence length | 2048 | +| Base precision | 4-bit (QLoRA) | +| Target modules | `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` | + +## Observed training loss + +Measured from our SLURM logs for this configuration. These are training-loss +observations only — no downstream benchmark evaluation has been run on this +model, so they should not be read as a quality claim. + +| SLURM job | Steps | First loss | Final loss | +| --- | --- | --- | --- | +| `45169147` | 1,310 | 1.7844 | 0.7491 | + +## Limitations + +- No benchmark evaluation has been run on this checkpoint. The only reported + numbers are training-loss observations. +- Inherits the biases, knowledge cutoff and failure modes of the base model. +- Fine-tuned on a single instruction-following dataset; behaviour outside that + distribution is untested. +- LoRA adapters were merged into the base weights, so the merged model cannot + be detached from this fine-tune. + +## Reproducing + +Trained by `notebooks/sft_distillation_fastcontext-4b-sft_unsloth.ipynb`, executed non-interactively with +papermill on a SLURM H100 partition (Unsloth + TRL, LoRA). + +--- + +*Card generated from the training run's own configuration and logs by* +*`scripts/generate_hub_model_card.py`.* diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..70adff8 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,61 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# 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' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- 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 %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..94cfb8c --- /dev/null +++ b/config.json @@ -0,0 +1,71 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "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", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 5000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "unsloth_version": "2026.4.6", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/model-00000-of-00002.safetensors b/model-00000-of-00002.safetensors new file mode 100644 index 0000000..190ff35 --- /dev/null +++ b/model-00000-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71097088c2fd13c7ba093905b09cb1807f609632b16fe1ac95d3946960d839fa +size 5355373240 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..1c33c96 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8505b57e11e15cf25f9d8e5154d96219802a3d1c38f93354c2c9dc18f785ab27 +size 2689608768 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..10a3654 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,405 @@ +{ + "metadata": { + "total_size": 8044936192 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00000-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00000-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00000-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00001-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..10c92fa --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476870a1f2fb6f6a2759a6ede2383bf9d5d738f17844563b65c91965b722ae09 +size 11422924 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..cb9c222 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,17 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [], + "is_local": false, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}" +} \ No newline at end of file