Colab:

Hugging face:

Colab Code:

#1安装微调库
%%capture
import torch
major_version, minor_version = torch.cuda.get_device_capability()
# 由于Colab有torch 2.2.1，会破坏软件包，要单独安装
!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
if major_version >= 8:
    # 新GPU，如Ampere、Hopper GPU（RTX 30xx、RTX 40xx、A100、H100、L40）。
    !pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes
else:
    # 较旧的GPU（V100、Tesla T4、RTX 20xx）
    !pip install --no-deps trl peft accelerate bitsandbytes
    !pip install xformers==0.0.25  #最新的0.0.26不兼容
pass

#2加载模型
from unsloth import FastLanguageModel
import torch
max_seq_length = 2048
dtype = None
load_in_4bit = True
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/llama-3-8b-bnb-4bit",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)

#3微调前测试
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}
### Input:
{}
### Response:
{}"""

FastLanguageModel.for_inference(model)
inputs = tokenizer(
[
    alpaca_prompt.format(
        "请用中文回答", # instruction
        "海绵宝宝的书法是不是叫做海绵体？", # input
        "", # output
    )
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)

#4准备微调数据集
EOS_TOKEN = tokenizer.eos_token # 必须添加 EOS_TOKEN
def formatting_prompts_func(examples):
    instructions = examples["instruction"]
    inputs       = examples["input"]
    outputs      = examples["output"]
    texts = []
    for instruction, input, output in zip(instructions, inputs, outputs):
        # 必须添加EOS_TOKEN，否则无限生成
        text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
        texts.append(text)
    return { "text" : texts, }
pass

from datasets import load_dataset
dataset = load_dataset("kigner/ruozhiba-llama3-tt", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)

#5设置训练参数
from trl import SFTTrainer
from transformers import TrainingArguments

model = FastLanguageModel.get_peft_model(
    model,
    r = 16, #  建议 8, 16, 32, 64, 128
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 16,
    lora_dropout = 0,
    bias = "none",
    use_gradient_checkpointing = "unsloth", # 检查点，长上下文度
    random_state = 3407,
    use_rslora = False,
    loftq_config = None,
)

trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    train_dataset = dataset,
    dataset_text_field = "text",
    max_seq_length = max_seq_length,
    dataset_num_proc = 2,
    packing = False, # 可以让短序列的训练速度提高5倍。
    args = TrainingArguments(
        per_device_train_batch_size = 2,
        gradient_accumulation_steps = 4,
        warmup_steps = 5,
        max_steps = 60,  # 微调步数
        learning_rate = 2e-4, # 学习率
        fp16 = not torch.cuda.is_bf16_supported(),
        bf16 = torch.cuda.is_bf16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "linear",
        seed = 3407,
        output_dir = "outputs",
    ),
)

#6开始训练
trainer_stats = trainer.train()

#7测试微调后的模型
FastLanguageModel.for_inference(model)
inputs = tokenizer(
[
    alpaca_prompt.format(
        "只用中文回答问题", # instruction
        "火烧赤壁 曹操为何不拨打119求救？", # input
        "", # output
    )
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)

#8保存LoRA模型
model.save_pretrained("lora_model") # Local saving
# model.push_to_hub("your_name/lora_model", token = "...") # 在线保存到hugging face，需要token

#9合并模型并量化成4位gguf保存
model.save_pretrained_gguf("model", tokenizer, quantization_method = "q4_k_m")
#model.save_pretrained_merged("outputs", tokenizer, save_method = "merged_16bit",) #合并模型，保存为16位hf
#model.push_to_hub_gguf("hf/model", tokenizer, quantization_method = "q4_k_m", token = "") #合并4位gguf，上传到hugging face(需要账号token)

#10挂载google drive
from google.colab import drive
drive.mount('/content/drive')

#11复制模型到google drive
import shutil
source_file = '/content/model-unsloth.Q4_K_M.gguf'
destination_dir = '/content/drive/MyDrive/Llama3'
destination_file = f'{destination_dir}/model-unsloth.Q4_K_M.gguf'
shutil.copy(source_file, destination_file)

GPT4ALL: