XTuner 大模型单卡低成本微调实战 ¶

import openpyxl
import json

def process_excel_to_json(input_file, output_file):
    # Load the workbook
    wb = openpyxl.load_workbook(input_file)

    # Select the "DrugQA" sheet
    sheet = wb["DrugQA"]

    # Initialize the output data structure
    output_data = []

    # Iterate through each row in column A and D
    for row in sheet.iter_rows(min_row=2, max_col=4, values_only=True):
        system_value = "You are a professional, highly experienced doctor professor. You always provide accurate, comprehensive, and detailed answers based on the patients' questions."

        # Create the conversation dictionary
        conversation = {
            "system": system_value,
            "input": row[0],
            "output": row[3]
        }

        # Append the conversation to the output data
        output_data.append({"conversation": [conversation]})

    # Write the output data to a JSON file
    with open(output_file, 'w', encoding='utf-8') as json_file:
        json.dump(output_data, json_file, indent=4)

    print(f"Conversion complete. Output written to {output_file}")

# Replace 'MedQA2019.xlsx' and 'output.jsonl' with your actual input and output file names
process_excel_to_json('MedQA2019.xlsx', 'output.jsonl')

import json
import random

def split_conversations(input_file, train_output_file, test_output_file):
    # Read the input JSONL file
    with open(input_file, 'r', encoding='utf-8') as jsonl_file:
        data = json.load(jsonl_file)

    # Count the number of conversation elements
    num_conversations = len(data)

    # Shuffle the data randomly
    random.shuffle(data)
    random.shuffle(data)
    random.shuffle(data)

    # Calculate the split points for train and test
    split_point = int(num_conversations * 0.7)

    # Split the data into train and test
    train_data = data[:split_point]
    test_data = data[split_point:]

    # Write the train data to a new JSONL file
    with open(train_output_file, 'w', encoding='utf-8') as train_jsonl_file:
        json.dump(train_data, train_jsonl_file, indent=4)

    # Write the test data to a new JSONL file
    with open(test_output_file, 'w', encoding='utf-8') as test_jsonl_file:
        json.dump(test_data, test_jsonl_file, indent=4)

    print(f"Split complete. Train data written to {train_output_file}, Test data written to {test_output_file}")

# Replace 'input.jsonl', 'train.jsonl', and 'test.jsonl' with your actual file names
split_conversations('MedQA2019-structured.jsonl', 'MedQA2019-structured-train.jsonl', 'MedQA2019-structured-test.jsonl')

import json

# 输入你的名字
name = '狙击美佐'
# 重复次数
n = 10000

data = [
    {
        "conversation": [
            {
                "input": "请做一下自我介绍",
                "output": "我是{}的小助手，内在是上海AI实验室书生·浦语的7B大模型哦".format(name)
            }
        ]
    }
]

for i in range(n):
    data.append(data[0])

with open('personal_assistant.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=4)

# Copyright (c) OpenMMLab. All rights reserved.
import torch
from bitsandbytes.optim import PagedAdamW32bit
from datasets import load_dataset
from mmengine.dataset import DefaultSampler
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
                            LoggerHook, ParamSchedulerHook)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR
from peft import LoraConfig
from transformers import (AutoModelForCausalLM, AutoTokenizer,
                        BitsAndBytesConfig)

from xtuner.dataset import process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import oasst1_map_fn, template_map_fn_factory
from xtuner.engine import DatasetInfoHook, EvaluateChatHook
from xtuner.model import SupervisedFinetune
from xtuner.utils import PROMPT_TEMPLATE

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
pretrained_model_name_or_path = '/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b'

# Data
data_path = '/root/personal_assistant/data/personal_assistant.json'
prompt_template = PROMPT_TEMPLATE.internlm_chat
max_length = 512
pack_to_max_length = True

# Scheduler & Optimizer
batch_size = 2  # per_device
accumulative_counts = 16
dataloader_num_workers = 0
max_epochs = 3
optim_type = PagedAdamW32bit
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1  # grad clip

# Evaluate the generation performance during the training
evaluation_freq = 90
SYSTEM = ''
evaluation_inputs = [ '请介绍一下你自己', '请做一下自我介绍' ]

#######################################################################
#                      PART 2  Model & Tokenizer                      #
#######################################################################
tokenizer = dict(
    type=AutoTokenizer.from_pretrained,
    pretrained_model_name_or_path=pretrained_model_name_or_path,
    trust_remote_code=True,
    padding_side='right')

model = dict(
    type=SupervisedFinetune,
    llm=dict(
        type=AutoModelForCausalLM.from_pretrained,
        pretrained_model_name_or_path=pretrained_model_name_or_path,
        trust_remote_code=True,
        torch_dtype=torch.float16,
        quantization_config=dict(
            type=BitsAndBytesConfig,
            load_in_4bit=True,
            load_in_8bit=False,
            llm_int8_threshold=6.0,
            llm_int8_has_fp16_weight=False,
            bnb_4bit_compute_dtype=torch.float16,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type='nf4')),
    lora=dict(
        type=LoraConfig,
        r=64,
        lora_alpha=16,
        lora_dropout=0.1,
        bias='none',
        task_type='CAUSAL_LM'))

#######################################################################
#                      PART 3  Dataset & Dataloader                   #
#######################################################################
train_dataset = dict(
    type=process_hf_dataset,
    dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path)),
    tokenizer=tokenizer,
    max_length=max_length,
    dataset_map_fn=None,
    template_map_fn=dict(
        type=template_map_fn_factory, template=prompt_template),
    remove_unused_columns=True,
    shuffle_before_pack=True,
    pack_to_max_length=pack_to_max_length)

train_dataloader = dict(
    batch_size=batch_size,
    num_workers=dataloader_num_workers,
    dataset=train_dataset,
    sampler=dict(type=DefaultSampler, shuffle=True),
    collate_fn=dict(type=default_collate_fn))

#######################################################################
#                    PART 4  Scheduler & Optimizer                    #
#######################################################################
# optimizer
optim_wrapper = dict(
    type=AmpOptimWrapper,
    optimizer=dict(
        type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
    clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
    accumulative_counts=accumulative_counts,
    loss_scale='dynamic',
    dtype='float16')

# learning policy
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md  # noqa: E501
param_scheduler = dict(
    type=CosineAnnealingLR,
    eta_min=0.0,
    by_epoch=True,
    T_max=max_epochs,
    convert_to_iter_based=True)

# train, val, test setting
train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)

#######################################################################
#                           PART 5  Runtime                           #
#######################################################################
# Log the dialogue periodically during the training process, optional
custom_hooks = [
    dict(type=DatasetInfoHook, tokenizer=tokenizer),
    dict(
        type=EvaluateChatHook,
        tokenizer=tokenizer,
        every_n_iters=evaluation_freq,
        evaluation_inputs=evaluation_inputs,
        system=SYSTEM,
        prompt_template=prompt_template)
]

# configure default hooks
default_hooks = dict(
    # record the time of every iteration.
    timer=dict(type=IterTimerHook),
    # print log every 100 iterations.
    logger=dict(type=LoggerHook, interval=10),
    # enable the parameter scheduler.
    param_scheduler=dict(type=ParamSchedulerHook),
    # save checkpoint per epoch.
    checkpoint=dict(type=CheckpointHook, interval=1),
    # set sampler seed in distributed evrionment.
    sampler_seed=dict(type=DistSamplerSeedHook),
)

# configure environment
env_cfg = dict(
    # whether to enable cudnn benchmark
    cudnn_benchmark=False,
    # set multi process parameters
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    # set distributed parameters
    dist_cfg=dict(backend='nccl'),
)

# set visualizer
visualizer = None

# set log level
log_level = 'INFO'

# load from which checkpoint
load_from = None

# whether to resume training from the loaded checkpoint
resume = False

# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)