* Add files via upload

* 新增ENmd文档

* Update README.md

* Update README_EN.md

* Update LICENSE

* [docs] update lmdeploy file

* add ocr.md

* Update tutorial.md

* Update tutorial_EN.md

* Update General_evaluation_EN.md

* Update General_evaluation_EN.md

* Update README.md

Add InternLM2_7B_chat_full's professional evaluation results

* Update Professional_evaluation.md

* Update Professional_evaluation.md

* Update Professional_evaluation.md

* Update Professional_evaluation.md

* Update Professional_evaluation_EN.md

* Update README.md

* Update README.md

* Update README_EN.md

* Update README_EN.md

* Update README_EN.md

* [DOC] update readme

* Update LICENSE

* Update LICENSE

* update personal info and small format optimizations

* update personal info and translations for contents in a table

* Update RAG README

* Update demo link in README.md

* Update xlab app link

* Update xlab link

* add xlab model

* Update web_demo-aiwei.py

* add bitex

---------

Co-authored-by: xzw <62385492+aJupyter@users.noreply.github.com>
Co-authored-by: এ許我辞忧࿐♡ <127636623+Smiling-Weeping-zhr@users.noreply.github.com>
Co-authored-by: Vicky <vicky_3021@163.com>
Co-authored-by: MING_X <119648793+MING-ZCH@users.noreply.github.com>
Co-authored-by: Nobody-ML <1755309985@qq.com>
Co-authored-by: 8baby8 <3345710651@qq.com>
Co-authored-by: chaoke <101492509+8baby8@users.noreply.github.com>
Co-authored-by: aJupyter <ajupyter@163.com>
Co-authored-by: HongCheng <kwchenghong@gmail.com>
Co-authored-by: santiagoTOP <“1537211712top@gmail.com”>

2024-03-15 19:51:04 +08:00

1.6 KiB

Raw Blame History

EmoLLM's professional evaluation

Introduction

This document describes a professional evaluation method and provides EmoLLM's scores on professional metrics.

Evaluation

The evaluation method, metric, and dataset from the paper《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》.

Metric: Comprehensiveness, Professionalism, Authenticity, Safety
Method: Turn-Based Dialogue Evaluation
Dataset: CPsyCounE

Result

Model:
- EmoLLM V1.0 (InternLM2_7B_chat_qlora)
- EmoLLM V2.0 (InternLM2_7B_chat_full)
Score：

Model	Comprehensiveness	Professionalism	Authenticity	Safety
InternLM2_7B_chat_qlora	1.32	2.20	2.10	1.00
InternLM2_7B_chat_full	1.40	2.45	2.24	1.00

Comparison

EmoLLM V2.0 is greatly improved in all scores compared to EmoLLM V1.0! Surpasses the performance of Role-playing ChatGPT on counseling tasks!
EmoLLM V1.0 is greatly improved on InternLM2_7B_Chat; Performance on the counseling task was similar compared to ChatGPT(Role-playing)
The comparison results are from the paper《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》

1.6 KiB Raw Blame History Unescape Escape