本地环境：cuda 11.7 torch2.1.0
项目文件结构：
1. 项目文件结构：
如果利用Llama Factory 进行微调主要会用到 LLama-Factory/src 中的文件
2. src 下的目录结构
本地推理的demo
通过api.py 进行 LLaMa-Factory 项目文件下运行，会有一个 web的demo
(可能需要修改 gradio 下面一个包的权限，创建一个公共的端口就可以)
CUDA_VISIBLE_DEVICES=1 python src/api.py --model_name_or_path LLama/Llama3-8B-Chinese-Chat --template llama3 我运行之后打不开 网址 所以 根据之前的 为了简单起见 还是用 cli_demo.py 放在 src 路径下
from llamafactory.chat import ChatModel from llamafactory.extras.misc import torch_gc try: import platform if platform.system() != "Windows": import readline # noqa: F401 except ImportError: print("Install `readline` for a better experience.") def main(): chat_model = ChatModel() messages = [] print("Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application.") while True: try: query = input("\nUser: ") except UnicodeDecodeError: print("Detected decoding error at the inputs, please set the terminal encoding to utf-8.") continue except Exception: raise if query.strip() == "exit": break if query.strip() == "clear": messages = [] torch_gc() print("History has been removed.") continue messages.append({"role": "user", "content": query}) print("Assistant: ", end="", flush=True) response = "" for new_text in chat_model.stream_chat(messages): print(new_text, end="", flush=True) response += new_text print() messages.append({"role": "assistant", "content": response}) if __name__ == "__main__": main()CUDA_VISIBLE_DEVICES=0 python src/cli_demo.py --model_name_or_path 自己模型地址 --template 和模型有关（看github 的 readme）遇到的问题：如果torch的版本低会有一个 BFloat16 的问题(开始是 2.0.1 报错了)
升级成 2.1.0 就好了
pytorch 官网 2.1.0 应该最低是cuda11.8 的 直接升级成这个就行 conda install 速度会快一些
可以在命令行进行展示：效果如下：
============= 以上是 2024.05.29 的 最新 LLaMa Factory 版本 =====================
本地微调：
再进行微调的时，主要就是 运行train.py 这个文件，但是需要指定一些参数 比如模型路径 数据集 微调方式等
train.py 内容
from llamafactory.train.tuner import run_exp def main(): run_exp() def _mp_fn(index): # For xla_spawn (TPUs) run_exp() if __name__ == "__main__": main() 可以看到 train.py 就是用到了 llamafactory.train.tuner ，所以进一步看一下 llamafactory 文件的目录结构
llamafactory/train 的 结构：
tuner.py 内容如下：python 相对导入：python 相对导入-CSDN博客
from typing import TYPE_CHECKING, Any, Dict, List, Optional import torch from transformers import PreTrainedModel from ..data import get_template_and_fix_tokenizer from ..extras.callbacks import LogCallback from ..extras.logging import get_logger from ..hparams import get_infer_args, get_train_args from ..model import load_model, load_tokenizer from .dpo import run_dpo from .kto import run_kto from .ppo import run_ppo from .pt import run_pt from .rm import run_rm from .sft import run_sft if TYPE_CHECKING: from transformers import TrainerCallback logger = get_logger(__name__) def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: List["TrainerCallback"] = []) -> None: model_args, data_args, training_args, finetuning_args, generating_args = get_train_args(args) callbacks.append(LogCallback(training_args.output_dir)) if finetuning_args.stage == "pt": run_pt(model_args, data_args, training_args, finetuning_args, callbacks) elif finetuning_args.stage == "sft": run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks) elif finetuning_args.stage == "rm": run_rm(model_args, data_args, training_args, finetuning_args, callbacks) elif finetuning_args.stage == "ppo": run_ppo(model_args, data_args, training_args, finetuning_args, generating_args, callbacks) elif finetuning_args.stage == "dpo": run_dpo(model_args, data_args, training_args, finetuning_args, callbacks) elif finetuning_args.stage == "kto": run_kto(model_args, data_args, training_args, finetuning_args, callbacks) else: raise ValueError("Unknown task.") def export_model(args: Optional[Dict[str, Any]] = None) -> None: model_args, data_args, finetuning_args, _ = get_infer_args(args) if model_args.export_dir is None: raise ValueError("Please specify `export_dir` to save model.") if model_args.adapter_name_or_path is not None and model_args.export_quantization_bit is not None: raise ValueError("Please merge adapters before quantizing the model.") tokenizer_module = load_tokenizer(model_args) tokenizer = tokenizer_module["tokenizer"] processor = tokenizer_module["processor"] get_template_and_fix_tokenizer(tokenizer, data_args.template) model = load_model(tokenizer, model_args, finetuning_args) # must after fixing tokenizer to resize vocab if getattr(model, "quantization_method", None) and model_args.adapter_name_or_path is not None: raise ValueError("Cannot merge adapters to a quantized model.") if not isinstance(model, PreTrainedModel): raise ValueError("The model is not a `PreTrainedModel`, export aborted.") if getattr(model, "quantization_method", None) is None: # cannot convert dtype of a quantized model output_dtype = getattr(model.config, "torch_dtype", torch.float16) setattr(model.config, "torch_dtype", output_dtype) model = model.to(output_dtype) else: setattr(model.config, "torch_dtype", torch.float16) model.save_pretrained( save_directory=model_args.export_dir, max_shard_size="{}GB".format(model_args.export_size), safe_serialization=(not model_args.export_legacy_format), ) if model_args.export_hub_model_id is not None: model.push_to_hub( model_args.export_hub_model_id, token=model_args.hf_hub_token, max_shard_size="{}GB".format(model_args.export_size), safe_serialization=(not model_args.export_legacy_format), ) try: tokenizer.padding_side = "left" # restore padding side tokenizer.init_kwargs["padding_side"] = "left" tokenizer.save_pretrained(model_args.export_dir) if model_args.export_hub_model_id is not None: tokenizer.push_to_hub(model_args.export_hub_model_id, token=model_args.hf_hub_token) if model_args.visual_inputs and processor is not None: getattr(processor, "image_processor").save_pretrained(model_args.export_dir) if model_args.export_hub_model_id is not None: getattr(processor, "image_processor").push_to_hub( model_args.export_hub_model_id, token=model_args.hf_hub_token ) except Exception: logger.warning("Cannot save tokenizer, please copy the files manually.") 可以看到 包含两个函数:
1. run_exp() 根据传入参数的不同选择不同的方式
2. export_model: 将原来的模型和微调之后的checkpoint 进行合并
到这里就基本上完成了 流程上的梳理 具体的微调方法需要到每个函数内部自行查看
======================= 以上 2024/05/27 ========================
怎么finetuning起来？
写一个脚本 train.sh ，放在 llama-factory 根目录下：终端运行 bash train.sh 即可
CUDA_VISIBLE_DEVICES=0 python src/train.py \ --stage sft \ --do_train True \ --model_name_or_path 自己模型的路径\ --finetuning_type lora \ --template default \ --flash_attn auto \ --dataset_dir data \ --dataset 自己的数据集\ --cutoff_len 1024 \ --learning_rate 5e-05 \ --num_train_epochs 1.0 \ --max_samples 100000 \ --per_device_train_batch_size 2 \ --gradient_accumulation_steps 8 \ --lr_scheduler_type cosine \ --max_grad_norm 1.0 \ --logging_steps 5 \ --save_steps 100 \ --warmup_steps 0 \ --optim adamw_torch \ --report_to none \ --output_dir 模型微调完成之后adapter的输出位置 \ --fp16 True \ --lora_rank 8 \ --lora_alpha 16 \ --lora_dropout 0 \ --lora_target q_proj,v_proj \ --plot_loss True具体的参数 batch_size ，lora_rank 需自行确定
推理：
CUDA_VISIBLE_DEVICES=0 python src/cli_demo.py --model_name_or_path 模型地址 --adapter_name_or_path 训练出来的适配器的位置 --template 提示词模版和模型相关即可成功 ！
注：暂时没用 vllm 框架，用的话可能问题较多
tokenllamactochatpythontpuappclifixidecodingtransformers2024apicodeassistantlegacytransformer数据集xing
