commit ecedb03dbd3730cc76000224c70c4cae0ebd2f44 Author: ModelHub XC Date: Mon Sep 28 19:21:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mamii76/Snowball-7B-Hybrid-HF 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..98ea47a --- /dev/null +++ b/README.md @@ -0,0 +1,50 @@ +--- +base_model: +- Qwen/Qwen2.5-7B +- open-thoughts/OpenThinker2-7B +- Qwen/Qwen2.5-Coder-7B-Instruct +library_name: transformers +tags: +- mergekit +- merge + +--- +# merged + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as a base. + +### Models Merged + +The following models were included in the merge: +* [open-thoughts/OpenThinker2-7B](https://huggingface.co/open-thoughts/OpenThinker2-7B) +* [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml + +models: + - model: open-thoughts/OpenThinker2-7B + parameters: + weight: 0.5 + density: 0.5 + - model: Qwen/Qwen2.5-Coder-7B-Instruct + parameters: + weight: 0.5 + density: 0.5 +merge_method: ties +base_model: Qwen/Qwen2.5-7B +dtype: bfloat16 +tokenizer_source: Qwen/Qwen2.5-Coder-7B-Instruct +parameters: + normalize: true + int8_mask: true + +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /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 %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- 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\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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..d61c864 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.12.1", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151665 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..2a16a89 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,17 @@ + +models: + - model: open-thoughts/OpenThinker2-7B + parameters: + weight: 0.5 + density: 0.5 + - model: Qwen/Qwen2.5-Coder-7B-Instruct + parameters: + weight: 0.5 + density: 0.5 +merge_method: ties +base_model: Qwen/Qwen2.5-7B +dtype: bfloat16 +tokenizer_source: Qwen/Qwen2.5-Coder-7B-Instruct +parameters: + normalize: true + int8_mask: true diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..48d15fb --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b942edafe1881050ff518a472c4935e51b18e4daa9e1ef456aabe44d81e29e +size 1087134848 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..2bdb318 --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0634a1b759dd820789bd80c58a5b0996a36843d2d277a7928308f3bbab229ad7 +size 1990007272 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..2261349 --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f2d6a2e3c24197d3c70a135fdb40327a00e3bd774f2b1a0e1eb5cf40706bd4 +size 1893836600 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..d28646b --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c266fe3d2550a8cf8fb8b3bdba3d9f5f5a5eebfe1f8edc4376cfd344b4d89f1f +size 1864467840 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..7caf900 --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77087ebca59adf3253036690e026706efa47cf815af47d5400aac3b864b74077 +size 1864467832 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..c10ce27 --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82cfc62923d8665f5808fd53345d001c168bd15cb5979b23156fcaa28c854513 +size 1864467840 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..73b069b --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37ac05b9747819d4c3c13f4c1b72c2a73742c84c438b894f0a51534362a506f +size 1864467832 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..de2388c --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2f6cf2087d56bbf08a335e07b4a1bcbcea6238b0266d8a72c317c949b08f0d +size 1864467792 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..3f9f29a --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41135ee360bd40dc41d713ce9d5f8c7b74659adef7580492849a64ad0ae1ab40 +size 932233872 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..75dd7ae --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_size": 15225512960, + "mergekit_version": "0.1.4" + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00009.safetensors", + "model.embed_tokens.weight": "model-00002-of-00009.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.4.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.norm.weight": "model-00009-of-00009.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..5156d16 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "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": false, + "local_files_only": false, + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}