14890fad56
* feat: add agents/actions/write_markdown * [ADD] add evaluation result of base model on 5/10 epochs * Rename mother.json to mother_v1_2439.json * Add files via upload * [DOC] update README * Update requirements.txt update mpi4py installation * Update README_EN.md update English comma * Update README.md 基于母亲角色的多轮对话模型微调完毕。已上传到 Huggingface。 * 多轮对话母亲角色的微调的脚本 * Update README.md 加上了王几行XING 和 思在 的作者信息 * Update README_EN.md * Update README.md * Update README_EN.md * Update README_EN.md * Changes to be committed: modified: .gitignore modified: README.md modified: README_EN.md new file: assets/EmoLLM_transparent.png deleted: assets/Shusheng.jpg new file: assets/Shusheng.png new file: assets/aiwei_demo1.gif new file: assets/aiwei_demo2.gif new file: assets/aiwei_demo3.gif new file: assets/aiwei_demo4.gif * Update README.md rectify aiwei_demo.gif * Update README.md rectify aiwei_demo style * Changes to be committed: modified: README.md modified: README_EN.md * Changes to be committed: modified: README.md modified: README_EN.md * [Doc] update readme * [Doc] update readme * Update README.md * Update README_EN.md * Update README.md * Update README_EN.md * Delete datasets/mother_v1_2439.json * Rename mother_v2_3838.json to mother_v2.json * Delete datasets/mother_v2.json * Add files via upload * Update README.md * Update README_EN.md * [Doc] Update README_EN.md minor fix * InternLM2-Base-7B QLoRA微调模型 链接和测评结果更新 * add download_model.py script, automatic download of model libraries * 清除图片的黑边、更新作者信息 modified: README.md new file: assets/aiwei_demo.gif deleted: assets/aiwei_demo1.gif modified: assets/aiwei_demo2.gif modified: assets/aiwei_demo3.gif modified: assets/aiwei_demo4.gif * rectify aiwei_demo transparent * transparent * modify: aiwei_demo table--->div * modified: aiwei_demo * modify: div ---> table * modified: README.md * modified: README_EN.md * update model config file links * Create internlm2_20b_chat_lora_alpaca_e3.py 20b模型的配置文件 * update model config file links update model config file links * Revert "update model config file links" --------- Co-authored-by: jujimeizuo <fengzetao.zed@foxmail.com> Co-authored-by: xzw <62385492+aJupyter@users.noreply.github.com> Co-authored-by: Zeyu Ba <72795264+ZeyuBa@users.noreply.github.com> Co-authored-by: Bryce Wang <90940753+brycewang2018@users.noreply.github.com> Co-authored-by: zealot52099 <songyan5209@163.com> Co-authored-by: HongCheng <kwchenghong@gmail.com> Co-authored-by: Yicong <yicooong@qq.com> Co-authored-by: Yicooong <54353406+Yicooong@users.noreply.github.com> Co-authored-by: aJupyter <ajupyter@163.com> Co-authored-by: MING_X <119648793+MING-ZCH@users.noreply.github.com> Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com> Co-authored-by: HatBoy <null2none@163.com> Co-authored-by: ZhouXinAo <142309012+zxazys@users.noreply.github.com>
53 lines
1.8 KiB
Markdown
53 lines
1.8 KiB
Markdown
# EmoLLM's general evaluation
|
|
|
|
## Introduction
|
|
|
|
This document provides instructions on how to use the 'eval.py' and 'metric.py' scripts. These scripts are used to evaluate the generation results of EmoLLM- a large model of mental health.
|
|
|
|
## Installation
|
|
|
|
- Python 3.x
|
|
- PyTorch
|
|
- Transformers
|
|
- Datasets
|
|
- NLTK
|
|
- Rouge
|
|
- Jieba
|
|
|
|
It can be installed using the following command:
|
|
|
|
```bash
|
|
pip install torch transformers datasets nltk rouge jieba
|
|
```
|
|
|
|
## Usage
|
|
|
|
### convert.py
|
|
|
|
Convert raw multi-round conversation data into single round data for evaluation.
|
|
|
|
### eval.py
|
|
|
|
The `eval.py` script is used to generate the doctor's response and evaluate it, mainly divided into the following parts:
|
|
|
|
1. Load the model and word divider.
|
|
2. Set test parameters, such as the number of test data and batch size.
|
|
3. Obtain data.
|
|
4. Generate responses and evaluate.
|
|
|
|
### metric.py
|
|
|
|
The `metric.py` script contains functions to calculate evaluation metrics, which can be set to evaluate by character level or word level, currently including BLEU and ROUGE scores.
|
|
|
|
## Results
|
|
|
|
Test the data in data.json with the following results:
|
|
|
|
| Model | ROUGE-1 | ROUGE-2 | ROUGE-L | BLEU-1 | BLEU-2 | BLEU-3 | BLEU-4 |
|
|
|----------|---------|---------|---------|---------|---------|---------|---------|
|
|
| Qwen1_5-0_5B-chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
|
|
| InternLM2_7B_chat_qlora | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
|
|
| InternLM2_7B_chat_full | 32.45% | 10.82% | 20.17% | 30.48% | 15.67% | 8.84% | 5.02% |
|
|
| InternLM2_7B_base_qlora_5epoch | 41.94% | 20.21% | 29.67% | 42.98% | 27.07% | 19.33% | 14.62% |
|
|
| InternLM2_7B_base_qlora_10epoch | 43.47% | 22.06% | 31.4% | 44.81% | 29.15% | 21.44% | 16.72% |
|