commit b86d03e0310672150c6c86f9bc3eda1688d598d6 Author: ModelHub XC Date: Thu May 28 16:46:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: GeneZC/MiniChat-3B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bc225d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f9cd534 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +frameworks: +- Pytorch +license: Apache License 2.0 +tasks: +- fill-mask +--- + +## MiniChat-3B + +📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B) + +❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2. + +A language model distilled and finetuned from an adapted version of LLaMA2-7B following "Towards the Law of Capacity Gap in Distilling Language Models". + +Outperforming a wide range of 3B competitors in GPT4 evaluation and even competing with several 7B chat models. + +teaser_b + +The following is an example code snippet to use MiniChat-3B: + +```python +import torch + +from transformers import AutoModelForCausalLM, AutoTokenizer + +from conversation import get_default_conv_template + +# MiniChat +tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniChat-3B", use_fast=False) +# GPU. +model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniChat-3B", use_cache=True, device_map="auto", torch_dtype=torch.float16).eval() +# CPU. +# model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniChat-3B", use_cache=True, device_map="cpu", torch_dtype=torch.float16).eval() + +conv = get_default_conv_template("minichat") + +question = "Implement a program to find the common elements in two arrays without using any extra data structures." +conv.append_message(conv.roles[0], question) +conv.append_message(conv.roles[1], None) +prompt = conv.get_prompt() +input_ids = tokenizer([prompt]).input_ids +output_ids = model.generate( + torch.as_tensor(input_ids).cuda(), + do_sample=True, + temperature=0.7, + max_new_tokens=1024, +) +output_ids = output_ids[0][len(input_ids[0]):] +output = tokenizer.decode(output_ids, skip_special_tokens=True).strip() +# output: "def common_elements(arr1, arr2):\n if len(arr1) == 0:\n return []\n if len(arr2) == 0:\n return arr1\n\n common_elements = []\n for element in arr1:\n if element in arr2:\n common_elements.append(element)\n\n return common_elements" +# Multiturn conversation could be realized by continuously appending questions to `conv`. +``` + +## Bibtex + +```bibtex +@article{zhang2023law, + title={Towards the Law of Capacity Gap in Distilling Language Models}, + author={Zhang, Chen and Song, Dawei and Ye, Zheyu and Gao, Yan}, + year={2023}, + url={https://arxiv.org/abs/2311.07052} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..768d098 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "MiniChat-3B", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 24, + "pad_token_id": 0, + "rms_norm_eps": 1e-05, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.30.2", + "use_cache": true, + "vocab_size": 49216 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..7b5b0c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"fill-mask"} \ No newline at end of file diff --git a/conversation.py b/conversation.py new file mode 100644 index 0000000..d4d9d2a --- /dev/null +++ b/conversation.py @@ -0,0 +1,223 @@ +""" +Conversation prompt templates. +""" + +import dataclasses +from enum import auto, Enum +from typing import List, Tuple, Any + + +class SeparatorStyle(Enum): + """Different separator style.""" + + ADD_COLON_SINGLE = auto() + ADD_COLON_TWO = auto() + NO_COLON_SINGLE = auto() + BAIZE = auto() + PHOENIX = auto() + MINICHAT = auto() + + +@dataclasses.dataclass +class Conversation: + """A class that keeps all conversation history.""" + + # System prompts + system: str + # Two roles + roles: List[str] + # All messages + messages: List[List[str]] + # Offset of few shot examples + offset: int + # Separator + sep_style: SeparatorStyle + sep: str + sep2: str = None + # Stop criteria (the default one is EOS token) + stop_str: str = None + # Stops generation if meeting any token in this list + stop_token_ids: List[int] = None + + # Used for the state in the gradio servers. + # TODO(lmzheng): refactor this + conv_id: Any = None + skip_next: bool = False + model_name: str = None + + def get_prompt(self): + if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE: + ret = self.system + self.sep + for role, message in self.messages: + if message: + ret += role + ": " + message + self.sep + else: + ret += role + ": " + return ret + elif self.sep_style == SeparatorStyle.ADD_COLON_TWO: + seps = [self.sep, self.sep2] + ret = self.system + seps[0] + for i, (role, message) in enumerate(self.messages): + if message: + ret += role + ": " + message + seps[i % 2] + else: + ret += role + ": " + return ret + elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE: + ret = self.system + for role, message in self.messages: + if message: + ret += role + message + self.sep + else: + ret += role + return ret + elif self.sep_style == SeparatorStyle.BAIZE: + ret = self.system + "\n" + for role, message in self.messages: + if message: + ret += role + message + "\n" + else: + ret += role + return ret + elif self.sep_style == SeparatorStyle.PHOENIX: + ret = self.system + for role, message in self.messages: + if message: + ret += role + ": " + "" + message + "" + else: + ret += role + ": " + "" + return ret + elif self.sep_style == SeparatorStyle.MINICHAT: + ret = self.system + for role, message in self.messages: + if message: + ret += role + " " + message + "" + else: + ret += role # No space is needed. + return ret + else: + raise ValueError(f"Invalid style: {self.sep_style}") + + def append_message(self, role, message): + self.messages.append([role, message]) + + def to_gradio_chatbot(self): + ret = [] + for i, (role, msg) in enumerate(self.messages[self.offset:]): + if i % 2 == 0: + ret.append([msg, None]) + else: + ret[-1][-1] = msg + return ret + + def to_openai_api_messages(self): + ret = [{"role": "system", "content": self.system}] + + for i, (_, msg) in enumerate(self.messages[self.offset:]): + if i % 2 == 0: + ret.append({"role": "user", "content": msg}) + else: + if msg is not None: + ret.append({"role": "assistant", "content": msg}) + return ret + + def copy(self): + return Conversation( + system=self.system, + roles=self.roles, + messages=[[x, y] for x, y in self.messages], + offset=self.offset, + sep_style=self.sep_style, + sep=self.sep, + sep2=self.sep2, + stop_str=self.stop_str, + stop_token_ids=self.stop_token_ids, + conv_id=self.conv_id, + model_name=self.model_name, + ) + + def dict(self): + return { + "system": self.system, + "roles": self.roles, + "messages": self.messages, + "offset": self.offset, + "conv_id": self.conv_id, + "model_name": self.model_name, + } + + +conv_vicuna = Conversation( + system="A chat between a curious user and an artificial intelligence assistant. " + "The assistant gives helpful, detailed, and polite answers to the user's questions.", + roles=("USER", "ASSISTANT"), + messages=(), + offset=0, + sep_style=SeparatorStyle.ADD_COLON_TWO, + sep=" ", + sep2="", +) + +conv_baize = Conversation( + system="The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n", + roles=("[|Human|]", "[|AI|]"), + messages=( + ("[|Human|]", "Hello!"), + ("[|AI|]", "Hi!"), + ), + offset=2, + sep_style=SeparatorStyle.BAIZE, + sep="\n", + stop_str="[|Human|]", +) + +conv_phoenix = Conversation( + system="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n", + roles=("Human", "Assistant"), + messages=(), + offset=0, + sep_style=SeparatorStyle.PHOENIX, + sep="", +) + +conv_chatgpt = Conversation( + system="You are a helpful assistant.", + roles=("user", "assistant"), + messages=(), + offset=0, + sep_style=None, + sep=None, +) + +conv_minichat = Conversation( + system="‘MiniChat’是一个由‘Beccurio’开发的AI语言模型。下面是人类和MiniChat之间的一段对话。MiniChat的回复应当尽可能详细，并且以Markdown的形式输出。MiniChat应当拒绝参与违背伦理的讨论。", + roles=("[|User|]", "[|Assistant|]"), + messages=(), + offset=0, + sep_style=SeparatorStyle.MINICHAT, + sep="", +) + + +conv_templates = { + "vicuna": conv_vicuna, + "baize": conv_baize, + "phoenix": conv_phoenix, + "chatgpt": conv_chatgpt, + "minichat": conv_minichat, +} + +def get_default_conv_template(model_name): + model_name = model_name.lower() + try: + ret = conv_templates[model_name] + return ret.copy() + except: + raise NotImplementedError(f"No support for model {model_name}.") + + +if __name__ == "__main__": + conv = conv_templates["minichat"].copy() + conv.append_message(conv.roles[0], "Write a Python function that checks if a given number is even or odd.") + conv.append_message(conv.roles[1], None) + print([conv.get_prompt()]) diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..ff9d756 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884f36cfbbd8a9c76f7f93ca354e34e9a5357d4a998f8eb274dd3e9053bd59ec +size 6040956605 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/teaser_b.jpg b/teaser_b.jpg new file mode 100644 index 0000000..f7d4732 Binary files /dev/null and b/teaser_b.jpg differ diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..14cb1e6 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae87c0db2b21b0fa3fdc5e19d1f9cea94efb703cc7c6281d8718a6714b3cc2be +size 748869 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..64f06a6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_fast": true +}