网站两侧广告,口碑营销的案例及分析,常德做网站专业公司,贵阳网站定制电话一、XTuner安装
1、代码准备
mkdir project
cd project
git clone https://github.com/InternLM/xtuner.git
2、环境准备
cd xtuner
pip install -r requirements.txt
#从源码安装
pip install -e .[all]
3、查看配置文件列表
XTuner 提供多个开箱即用的配置文件#xf…一、XTuner安装
1、代码准备
mkdir project
cd project
git clone https://github.com/InternLM/xtuner.git
2、环境准备
cd xtuner
pip install -r requirements.txt
#从源码安装
pip install -e .[all]
3、查看配置文件列表
XTuner 提供多个开箱即用的配置文件用户可以通过下列命令查看
#列出所有内置配置文件
xtuner list-cfg
#列出internlm2大模型的相关配置文件
xtuner list-cfg | grep internlm2
二、大模型微调步骤
1、大模型下载
cd /root/share/model_repos/
git clone https://www.modelscope.cn/Shanghai_AI_Laboratory/internlm2-chat-7b.git
2、微调数据准备
2.1、获取原始数据
以Medication_QA数据为例
原始数据格式 取其中的“Question”和“Answer”来做数据集
2.2、将数据转为 XTuner 的数据格式
XTuner的数据格式.jsonl
[{conversation:[{system: xxx,input: xxx,output: xxx}]
},
{conversation:[{system: xxx,input: xxx,output: xxx}]
}]
每一条原始数据对应一条“conversation”对应关系为:
input 对应 Question
output 对应 Answer
system 全部设置为“You are a professional, highly experienced doctor professor. You always provide accurate, comprehensive, and detailed answers based on the patients questions.”
格式化后的数据 数据转换代码如下xlsx2jsonl.py
import openpyxl
import jsondef process_excel_to_json(input_file, output_file):# Load the workbookwb openpyxl.load_workbook(input_file)# Select the DrugQA sheetsheet wb[DrugQA]# Initialize the output data structureoutput_data []# Iterate through each row in column A and Dfor row in sheet.iter_rows(min_row2, max_col4, values_onlyTrue):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 dictionaryconversation {system: system_value,input: row[0],output: row[3]}# Append the conversation to the output dataoutput_data.append({conversation: [conversation]})# Write the output data to a JSON filewith open(output_file, w, encodingutf-8) as json_file:json.dump(output_data, json_file, indent4)print(fConversion complete. Output written to {output_file})# Replace MedQA2019.xlsx and output.jsonl with your actual input and output file names
process_excel_to_json(MedInfo2019-QA-Medications.xlsx, output.jsonl)
2.3、切分出训练集和测试集7:3
import json
import randomdef split_conversations(input_file, train_output_file, test_output_file):# Read the input JSONL filewith open(input_file, r, encodingutf-8) as jsonl_file:data json.load(jsonl_file)# Count the number of conversation elementsnum_conversations len(data)# Shuffle the data randomlyrandom.shuffle(data)random.shuffle(data)random.shuffle(data)# Calculate the split points for train and testsplit_point int(num_conversations * 0.7)# Split the data into train and testtrain_data data[:split_point]test_data data[split_point:]# Write the train data to a new JSONL filewith open(train_output_file, w, encodingutf-8) as train_jsonl_file:json.dump(train_data, train_jsonl_file, indent4)# Write the test data to a new JSONL filewith open(test_output_file, w, encodingutf-8) as test_jsonl_file:json.dump(test_data, test_jsonl_file, indent4)print(fSplit 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(output.jsonl, MedQA2019-structured-train.jsonl, MedQA2019-structured-test.jsonl)
3、配置文件准备
根据所选用的大模型下载对应的配置文件
xtuner copy-cfg internlm2_chat_7b_qlora_oasst1_e3_copy.py .
# 修改import部分
- from xtuner.dataset.map_fns import oasst1_map_fn, template_map_fn_factoryfrom xtuner.dataset.map_fns import template_map_fn_factory# 修改模型为本地路径
- pretrained_model_name_or_path internlm/internlm-chat-7bpretrained_model_name_or_path /root/share/model_repos/internlm2-chat-7b# 修改训练数据为 MedQA2019-structured-train.jsonl 路径
- data_path timdettmers/openassistant-guanacodata_path MedQA2019-structured-train.jsonl# 修改 train_dataset 对象
train_dataset dict(typeprocess_hf_dataset,
- datasetdict(typeload_dataset, pathdata_path),datasetdict(typeload_dataset, pathjson, data_filesdict(traindata_path)),tokenizertokenizer,max_lengthmax_length,
- dataset_map_fnalpaca_map_fn,dataset_map_fnNone,template_map_fndict(typetemplate_map_fn_factory, templateprompt_template),remove_unused_columnsTrue,shuffle_before_packTrue,pack_to_max_lengthpack_to_max_length)
4、启动微调
xtuner train internlm2_chat_7b_qlora_oasst1_e3_copy.py --deepspeed deepspeed_zero2
5、将得到的 PTH 模型转换为 HuggingFace 模型即生成 Adapter 文件夹
mkdir hf
export MKL_SERVICE_FORCE_INTEL1
export MKL_THREADING_LAYERGNU
xtuner convert pth_to_hf internlm2_chat_7b_qlora_oasst1_e3_copy.py ./work_dirs/internlm2_chat_7b_qlora_oasst1_e3_copy/iter_96.pth ./hf
hf 文件夹即为我们平时所理解的所谓 “LoRA 模型文件”
6、将 HuggingFace adapter 合并到大语言模型
xtuner convert merge /root/share/model_repos/internlm2-chat-7b ./hf ./merged --max-shard-size 2GB
# xtuner convert merge \
# ${NAME_OR_PATH_TO_LLM} \
# ${NAME_OR_PATH_TO_ADAPTER} \
# ${SAVE_PATH} \
# --max-shard-size 2GB
./merged 文件夹中既微调后的大模型使用方法和原模型一样internlm2-chat-7b
