lm-sys/FastChat

Chat Arena version of fastchat-t5-3b-v1.0 provides more refined answers than standard Huggingface model.

Open

#1,264 建立於 2023年5月15日

在 GitHub 查看
 (26 留言) (3 反應) (1 負責人)Python (38,959 star) (4,736 fork)batch import
documentationgood first issuequestion

描述

Hello - I notice that the chat arena version of fastchat-t5-3b-v1.0 provides quite different answers from the model compared to when it is downloaded manually and run using fastchat.serve.cli --model-path lmsys/fastchat-t5-3b-v1.0. What is the reason for this difference? Are there any special prompt templates or prompt tuning that gives the chat arena version its better responses?

貢獻者指南

技術棧
pythonpytorch
領域
machine learningai
議題類型
research
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-3 hours
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
needs maintainer response
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
PythonFastChat basicsPrompt engineering basics
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
30
研究方向
Investigate the differences between the Chat Arena version and standard Huggingface model of fastchat t5-3b v1.0. Check the FastChat source code for any special prompt templates or prompt tuning used in the arena mode (e.g., files like fastchat/serve/ or fastchat/train/). Look at the model card and any configuration differences. Consider the discussion in the issue comments for hints.