emotion_diff

Emotio_diff模型

简介：本模型是基于swift框架，对qwe-7b-chat模型进行微调获得的。模型的功能是评估用户输入的一段话，模型能够准确给出这句话是消极的还是积极的。

1.实验环境

swift框架 ubutu 22.04 cuda 12.0.1 pytho 3.10 pytorch 2.1.2

2.训练方法

数据集：jdsetimetzh

微调的模型：qwe-7b-chat

3.训练的步骤

3.1使用modelscope上的免费的GPU算力

3.2启动后进入命令行界面

3.3安装swift

通过以下命令安装

git cloe https://github.com/modelscope/swift.git
cd swift
pip istall -e .[llm]

4.微调代码

import os

os.eviro['CUDA_VISIBLE_DEVICES'] = '0'

import torch

from swift.llm import (

DatasetName, IferArgumets, ModelType, SftArgumets,

ifer_mai, sft_mai, app_ui_mai, merge_lora_mai

)

model_type = ModelType.qwe_7b_chat

sft_args = SftArgumets(

model_type=model_type,

trai_dataset_sample=2000,

dataset=[DatasetName.jd_setimet_zh],

output_dir='output')

result = sft_mai(sft_args)

best_model_checkpoit = result['best_model_checkpoit']

prit(f'best_model_checkpoit: {best_model_checkpoit}')

torch.cuda.empty_cache()

ifer_args = IferArgumets(

ckpt_dir=best_model_checkpoit,

show_dataset_sample=10)

# merge_lora_mai(ifer_args)

result = ifer_mai(ifer_args)

5.示例代码

import os

os.eviro['CUDA_VISIBLE_DEVICES'] = '0'

import torch

from swift.llm import (

DatasetName, IferArgumets, ModelType, SftArgumets,

ifer_mai, sft_mai, app_ui_mai, merge_lora_mai

)

best_model_checkpoit = "/mt/workspace/output/qwe-7b-chat/v0-20240123-102915/checkpoit-100"

prit(f'best_model_checkpoit: {best_model_checkpoit}')

torch.cuda.empty_cache()

ifer_args = IferArgumets(

ckpt_dir=best_model_checkpoit,

show_dataset_sample=10)

# merge_lora_mai(ifer_args)

ifer_args.system="You are a expert i aalyzig emotios. The user will give some Chiese or Eglish seteces, ad you oly eed to aswer whether the emotio i the setece is 'positive' or 'agetive'. For example, the user iputs {Quality is very good, the material is very good, the workmaship is exquisite, the style is ice, the clothes are very beautiful}. Your aswer is {positive}. Besides the emotioal type of the setece (positive, egative), you do't eed to aswer ay other redudat words."

prit(f"ifer_args-->{ifer_args.system}")

result = ifer_mai(ifer_args)

torch.cuda.empty_cache()

6.结果

Emotion_diff模型 简介：本模型是基于swift框架，对qwen-7b-chat模型进行微调获得的。模型的功能是评估用户输入的一段话，模型能够准确给出这句话是消极的还是积极的。 1.实验环境