commit 4dbd81238649ae377783768bc4b9f6c1a95bfdb4 Author: ModelHub XC Date: Mon Jul 13 13:38:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: sarrington/qwen2.5-0.5b-spliced Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8322e55 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +gemma_spliced_fresh_iq4xs.gguf filter=lfs diff=lfs merge=lfs -text +gemma_spliced_fresh_q4km.gguf 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..36eecdb --- /dev/null +++ b/README.md @@ -0,0 +1,29 @@ +--- +language: +- en +license: apache-2.0 +tags: +- qwen +- qwen2.5 +- text-generation +- gguf +- local-ai +- apple-silicon +--- + +# Qwen 2.5 0.5B Spliced GGUF + +A highly optimized, 15-layer spliced variant of the **Qwen 2.5 0.5B** architecture. + +## Model Description +This repository contains the spliced mixed-precision weights of Qwen 2.5 0.5B, surgically pruned from 16 layers to 15 layers. It features standard configs and tokenizer support for seamless local execution on mobile and edge platforms. + +* **Format**: Safetensors / GGUF (`Q4_K_M`, `IQ4_XS`) +* **Size**: 284 MB (GGUF) / 257 MB (IQ4_XS) +* **Target Platforms**: Apple Silicon MacBooks (M1/M2/M3/M4) and standard CPU/GPU local runtimes. + +## Local Quickstart +Run the model natively via standard `llama-cli`: +```bash +llama-cli -ngl 100 -m ./gemma_spliced_fresh_q4km.gguf -p "The mathematical beauty of wavelets lies in" -n 128 +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..28028c0 --- /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 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 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..8edf8c5 --- /dev/null +++ b/config.json @@ -0,0 +1,49 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 15, + "model_type": "qwen2", + "num_attention_heads": 14, + "num_hidden_layers": 15, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.5.1", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/gemma_spliced_fresh_iq4xs.gguf b/gemma_spliced_fresh_iq4xs.gguf new file mode 100644 index 0000000..e4da119 --- /dev/null +++ b/gemma_spliced_fresh_iq4xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4573cf6973123c1bb0cdd1bf74fa68a52d264c3fb64b9febcea8b7961493b397 +size 275523616 diff --git a/gemma_spliced_fresh_q4km.gguf b/gemma_spliced_fresh_q4km.gguf new file mode 100644 index 0000000..6f6dc27 --- /dev/null +++ b/gemma_spliced_fresh_q4km.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f7ae95077d78d1de29227448239f423daa9a5d3d626c6595e80ac13eebfb8c +size 304512800 diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..50f331a --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a0151ae03153fc54066efac66b16d9462db8f7f6e32af0b81be76e0cccaa7c5 +size 379182424 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..f3b01fc --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e4f8694fb8fa8373b9221eba9cd7aa90eaee6b464089d199558155dabd8a14 +size 98426408 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..3e6e435 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1aa3319cbfb8bd5ed38140837fa6c462bbcf6e1000870716decdcf3d9fb5dc +size 92691960 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..fb92bf1 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0b31aec23bb6e8fb199af1ee3dbb01379a1ef8a14ec5cc1e45fe8cc00d9438 +size 107142392 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..9bf7a0e --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561c226b1e42fd321755a9e51acb611c98bd002fedca60bf80bb34716bcb6997 +size 42219328 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..7c521c3 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,189 @@ +{ + "metadata": { + "total_size": 719642624 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.norm.weight": "model-00005-of-00005.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..1ce8d7b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "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, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}