commit 056fb37e2701cfd7b12e225a000e1024e946afab Author: ModelHub XC Date: Wed Jun 10 15:58:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: dizza01/qwen2.5-7b-bib-grounded-sft-merged 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..bc5f30d --- /dev/null +++ b/README.md @@ -0,0 +1,199 @@ +--- +library_name: transformers +tags: [] +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + +This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] \ No newline at end of file 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..001b84e --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.8.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8b6cdd7 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.8.0" +} diff --git a/handler.py b/handler.py new file mode 100644 index 0000000..6cee370 --- /dev/null +++ b/handler.py @@ -0,0 +1,126 @@ +import os +import json +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer +from peft import AutoPeftModelForCausalLM + +DEFAULT_SYSTEM_PROMPT = ( + "You are a QA assistant. " + "Use only the provided context. " + "If the answer is not present in the context, say so clearly." +) + +class EndpointHandler: + def __init__(self, path: str = ""): + model_dir = path or "/repository" + + self.tokenizer = AutoTokenizer.from_pretrained( + model_dir, + trust_remote_code=True, + ) + + if self.tokenizer.pad_token_id is None: + self.tokenizer.pad_token = self.tokenizer.eos_token + + dtype = torch.float16 if torch.cuda.is_available() else torch.float32 + + adapter_config_path = os.path.join(model_dir, "adapter_config.json") + if os.path.exists(adapter_config_path): + self.model = AutoPeftModelForCausalLM.from_pretrained( + model_dir, + trust_remote_code=True, + torch_dtype=dtype, + low_cpu_mem_usage=True, + device_map="auto" if torch.cuda.is_available() else None, + ) + else: + self.model = AutoModelForCausalLM.from_pretrained( + model_dir, + trust_remote_code=True, + torch_dtype=dtype, + low_cpu_mem_usage=True, + device_map="auto" if torch.cuda.is_available() else None, + ) + + self.model.eval() + + def _build_messages(self, inputs): + if isinstance(inputs, list): + messages = inputs + elif isinstance(inputs, dict) and "context" in inputs and "question" in inputs: + messages = [ + {"role": "system", "content": DEFAULT_SYSTEM_PROMPT}, + { + "role": "user", + "content": f"Context:\n{inputs['context']}\n\nQuestion: {inputs['question']}", + }, + ] + else: + messages = [ + {"role": "system", "content": DEFAULT_SYSTEM_PROMPT}, + {"role": "user", "content": str(inputs)}, + ] + + has_system = any(message.get("role") == "system" for message in messages) + if not has_system: + messages = [{"role": "system", "content": DEFAULT_SYSTEM_PROMPT}] + messages + + return messages + + def __call__(self, data): + inputs = data.get("inputs", "") + params = data.get("parameters", {}) or {} + + max_new_tokens = min(int(params.get("max_new_tokens", 128)), 512) + temperature = float(params.get("temperature", 0.0)) + top_p = float(params.get("top_p", 1.0)) + do_sample = bool(params.get("do_sample", False)) + repetition_penalty = float(params.get("repetition_penalty", 1.0)) + no_repeat_ngram_size = int(params.get("no_repeat_ngram_size", 0)) + debug = bool(params.get("debug", False)) + + messages = self._build_messages(inputs) + + prompt = self.tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, + ) + + enc = self.tokenizer( + prompt, + return_tensors="pt", + truncation=True, + max_length=min(getattr(self.tokenizer, "model_max_length", 4096), 4096), + ) + + if torch.cuda.is_available(): + enc = {key: value.to(self.model.device) for key, value in enc.items()} + + generate_kwargs = dict( + **enc, + max_new_tokens=max_new_tokens, + do_sample=do_sample, + repetition_penalty=repetition_penalty, + pad_token_id=self.tokenizer.pad_token_id, + eos_token_id=self.tokenizer.eos_token_id, + ) + + if do_sample: + generate_kwargs["temperature"] = max(temperature, 1e-5) + generate_kwargs["top_p"] = top_p + + if no_repeat_ngram_size > 0: + generate_kwargs["no_repeat_ngram_size"] = no_repeat_ngram_size + + with torch.no_grad(): + out = self.model.generate(**generate_kwargs) + + generated_ids = out[0][enc["input_ids"].shape[-1]:] + text = self.tokenizer.decode(generated_ids, skip_special_tokens=True).strip() + + response = {"generated_text": text} + if debug: + response["prompt"] = prompt + response["messages"] = messages + return response \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..b2f93e3 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:224962030b8430ebaf3114582300389722ccc726bf327f02203fe557463490fe +size 15231272152 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..5835dec --- /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_start|>", + "im_end": "<|im_end|>", + "object_ref_start": "<|object_ref_start|>", + "object_ref_end": "<|object_ref_end|>", + "box_start": "<|box_start|>", + "box_end": "<|box_end|>", + "quad_start": "<|quad_start|>", + "quad_end": "<|quad_end|>", + "vision_start": "<|vision_start|>", + "vision_end": "<|vision_end|>", + "vision_pad": "<|vision_pad|>", + "image_pad": "<|image_pad|>", + "video_pad": "<|video_pad|>" +}, + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}