commit 22c53076e7e603fa9a71fdb7a5285e3cec9d5608 Author: ModelHub XC Date: Mon May 25 11:48:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: amphora/Qwen3-4B-DASD-32K 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..20def9b --- /dev/null +++ b/README.md @@ -0,0 +1,23 @@ +--- +base_model: unsloth/Qwen3-4B-Instruct-2507 +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +- trl +- sft +license: apache-2.0 +language: +- en +--- + +# Uploaded model + +- **Developed by:** amphora +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/Qwen3-4B-Instruct-2507 + +This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) + +[](https://github.com/unslothai/unsloth) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..8ad2f87 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,144 @@ + +{%- if tools %} + {{- '<|im_start|>system +' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + ' + +' }} + {%- endif %} + {{- "# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: +" }} + {%- for tool in tools %} + {{- " +" }} + {{- tool | tojson }} + {%- endfor %} + {{- " + + +For each function call, return a json object with function name and arguments within XML tags: + +{\"name\": , \"arguments\": } +<|im_end|> +" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system +' + messages[0].content + '<|im_end|> +' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for forward_message in messages %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- set message = messages[index] %} + {%- set current_content = message.content if message.content is not none else '' %} + {%- set tool_start = '' %} + {%- set tool_start_length = tool_start|length %} + {%- set start_of_message = current_content[:tool_start_length] %} + {%- set tool_end = '' %} + {%- set tool_end_length = tool_end|length %} + {%- set start_pos = (current_content|length) - tool_end_length %} + {%- if start_pos < 0 %} + {%- set start_pos = 0 %} + {%- endif %} + {%- set end_of_message = current_content[start_pos:] %} + {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + ' +' + message.content + '<|im_end|>' + ' +' }} + {%- elif message.role == "assistant" %} + {%- set content = message.content %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is defined and message.reasoning_content is not none %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in message.content %} + {%- set content = (message.content.split('')|last).lstrip(' +') %} + {%- set reasoning_content = (message.content.split('')|first).rstrip(' +') %} + {%- set reasoning_content = (reasoning_content.split('')|last).lstrip(' +') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + ' + +' + reasoning_content.strip(' +') + ' + + +' + content.lstrip(' +') }} + {%- else %} + {{- '<|im_start|>' + message.role + ' +' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + ' +' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- ' +' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- ' +{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '} +' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|> +' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- ' + +' }} + {{- message.content }} + {{- ' +' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|> +' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant +' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- ' + + + +' }} + {%- endif %} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..6904f5e --- /dev/null +++ b/config.json @@ -0,0 +1,74 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "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_name": "unsloth/Qwen3-4B-Instruct-2507", + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151669, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 5000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.5.0", + "unsloth_fixed": true, + "unsloth_version": "2026.5.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..fcbb1f0 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 262144, + "pad_token_id": 151669, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..ea68693 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ead75f9eca7a44da77057b8c5d104a1215c610a931c6e4cffa88630e7be5874 +size 8044982080 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..73037fe --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112 +size 11422840 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..1c7a1e6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": true, + "model_max_length": 262144, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}