lm-sys/FastChat

[Feature Request] Support InternLM Deploy

Open

#2,403 建立於 2023年9月12日

在 GitHub 查看
 (2 留言) (0 反應) (0 負責人)Python (38,959 star) (4,736 fork)batch import
good first issue

描述

Dear FastChat developer,

Greetings! I am vansinhu, a community developer and volunteer at InternLM. InternLM is a large language model similar to llama2, and we look forward to InternLM being supported in FastChat. If there are any challenges or inquiries regarding support for InternLM, please feel free to join our Discord discussion at https://discord.gg/gF9ezcmtM3.

Best regards, vansinhu

貢獻者指南

技術棧
pythonpytorch
領域
backendmachine learningapi
議題類型
feature
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。
3
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。
1-2 days
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。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
needs investigation
前置要求
Familiarity with FastChat codebaseUnderstanding of LLM model loading
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 existing model integrations in fastchat/model/model adapter.py, especially the Llama or Vicuna adapters. Understand the model registration and inference pipeline. Look at InternLM's Hugging Face page for model weights and tokenizer. Check if there are any linked discussions or comments from maintainers for additional context. Consider starting a draft PR to initiate the integration.