LLM微调（二）| 微调LLAMA-2和其他开源LLM的两种简单方法

本文介绍: TRL是一个全栈库，提供了通过强化学习来训练transformer语言模型一系列工具，包括从监督微调步骤（SFT）、奖励建模步骤（RM）到近端策略优化（PPO）步骤。AutoTrain是一种无代码工具，用于为自然语言处理（NLP）任务、计算机视觉（CV）任务、语音任务甚至表格任务训练最先进的模型。: 如果要存储微调好的模型到Hugging Face，需要指定repository ID。: 指定微调所需要的数据，可以使用huggingface上的数据集。: 设置模型最大上下文窗口。: 需要微调的基础模型。

本文将介绍两种开源工具来微调LLAMA-2。

AutoTrain是一种无代码工具，用于为自然语言处理（NLP）任务、计算机视觉（CV）任务、语音任务甚至表格任务训练最先进的模型。

!pip install autotrain-advanced!pip install huggingface_hub

# update torch!autotrain setup --update-torch

# Login to huggingfacefrom huggingface_hub import notebook_loginnotebook_login()

! autotrain llm --train --model {MODEL_NAME} --project-name {PROJECT_NAME} --data-path data/ --text-column text --lr {LEARNING_RATE} --batch-size {BATCH_SIZE} --epochs {NUM_EPOCHS} --block-size {BLOCK_SIZE} --warmup-ratio {WARMUP_RATIO} --lora-r {LORA_R} --lora-alpha {LORA_ALPHA} --lora-dropout {LORA_DROPOUT} --weight-decay {WEIGHT_DECAY} --gradient-accumulation {GRADIENT_ACCUMULATION}

核心参数含义：

llm: 微调模型的类型

— project_name: 项目名称

— model: 需要微调的基础模型

!autotrain llm--train--project_name "llama2-autotrain-openassitant"--model TinyPixel/Llama-2-7B-bf16-sharded--data_path timdettmers/openassistant-guanaco--text_column text--use_peft--use_int4--learning_rate 0.4--train_batch_size 3--num_train_epochs 2--trainer sft--model_max_length 1048--push_to_hub--repo_id trojrobert/llama2-autotrain-openassistant--block_size 1048 > training.log

!pip install -q -U trl peft transformers  datasets bitsandbytes wandb

from datasets import load_datasetdataset_name = "timdettmers/openassistant-guanaco"dataset = load_dataset(dataset_name, split="train")

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig# quantizition configurationbnb_config = BitsAndBytesConfig(    load_in_4bit=True,    bnb_4bit_quant_type="nf4",    bnb_4bit_compute_dtype=torch.float16,)# download modelmodel_name = "TinyPixel/Llama-2-7B-bf16-sharded"model = AutoModelForCausalLM.from_pretrained(    model_name,    quantization_config=bnb_config,    trust_remote_code=True)model.config.use_cache = False

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)tokenizer.pad_token = tokenizer.eos_token

from peft import LoraConfig, get_peft_modellora_alpha = 16lora_dropout = 0.1lora_r = 64peft_config = LoraConfig(    lora_alpha=lora_alpha,    lora_dropout=lora_dropout,    r=lora_r,    bias="none",    task_type="CAUSAL_LM")

from transformers import TrainingArgumentsoutput_dir = "./results"per_device_train_batch_size = 4gradient_accumulation_steps = 4optim = "paged_adamw_32bit"save_steps = 100logging_steps = 10learning_rate = 2e-4max_grad_norm = 0.3max_steps = 100warmup_ratio = 0.03lr_scheduler_type = "constant"training_arguments = TrainingArguments(    output_dir=output_dir,    per_device_train_batch_size=per_device_train_batch_size,    gradient_accumulation_steps=gradient_accumulation_steps,    optim=optim,    save_steps=save_steps,    logging_steps=logging_steps,    learning_rate=learning_rate,    fp16=True,    max_grad_norm=max_grad_norm,    max_steps=max_steps,    warmup_ratio=warmup_ratio,    group_by_length=True,    lr_scheduler_type=lr_scheduler_type,)

from trl import SFTTrainermax_seq_length = 512trainer = SFTTrainer(    model=model,    train_dataset=dataset,    peft_config=peft_config,    dataset_text_field="text",    max_seq_length=max_seq_length,    tokenizer=tokenizer,    args=training_arguments,)

for name, module in trainer.model.named_modules():    if "norm" in name:        module = module.to(torch.float32)

trainer.train()

model_to_save = trainer.model.module if hasattr(trainer.model, 'module') else trainer.model  # Take care of distributed/parallel trainingmodel_to_save.save_pretrained("outputs")

lora_config = LoraConfig.from_pretrained('outputs')tuned_model = get_peft_model(model, lora_config)

text = "What is a large language model?"device = "cuda:0"inputs = tokenizer(text, return_tensors="pt").to(device)outputs = tuned_model.generate(**inputs, max_new_tokens=50)print(tokenizer.decode(outputs[0], skip_special_tokens=True))