github.com/lm-sys/FastChat issues | Ecosyste.ms: OpenCollective

Could not find the transformer layer class to wrap in the model.

Jerry-hyl opened this issue 6 months ago

prompt will always be truncated

jiaoyangkuohai opened this issue 6 months ago

Update monitor.py

smartdolphin opened this pull request 6 months ago

Gradio web server requires model-worker deps

ketsapiwiq opened this issue 6 months ago

Fine-tuning Vicuna-7B

dhruvpes opened this issue 6 months ago

Implement GLM-4 models

plyu3 opened this issue 6 months ago

Fixes for vision arena to operation

BabyChouSr opened this pull request 6 months ago

Add AutoCoder LLM

upintheairsheep opened this issue 7 months ago

Add Character.AI's C1.0, C1.1, C1.2

upintheairsheep opened this issue 7 months ago

Add xAI Grok-1

upintheairsheep opened this issue 7 months ago

Fix Semaphore release Issue in `api_generate_stream` Function of vllm_worker

coolbeevip opened this pull request 7 months ago

Semaphore release Issue in api_generate_stream Function of vllm_worker

coolbeevip opened this issue 7 months ago

Merge vision arena code with operation

BabyChouSr opened this pull request 7 months ago

Add support for the Korean language

smartdolphin opened this issue 7 months ago

The accuracy issue of MT bench

Luoqiu76 opened this issue 7 months ago

fix ranking

infwinston opened this pull request 7 months ago

Where could I get the code for https://chat.lmsys.org/

JunityZhan opened this issue 7 months ago

当我试图集成chatglm2-6b的时候发现如下错误

moonlightnoodles opened this issue 7 months ago

how to adapting GLM4 & QWEN2 to FastChat

Damonpkl opened this issue 7 months ago

FastChat Code base help

saikumar-cloudangles opened this issue 7 months ago

generate Vicuna error

wen020 opened this issue 7 months ago

how to submit with enter

crischeng opened this issue 7 months ago

updated vqa examples

lisadunlap opened this pull request 7 months ago

How does calibrating for an anchor model in `elo_analysis` affect the elo ratings and bootstrap CIs?

acylam opened this issue 7 months ago

update leaderboard description

infwinston opened this pull request 7 months ago

Update monitor.py

infwinston opened this pull request 7 months ago

how to customize free-style LLM?

jxgu1016 opened this issue 7 months ago

Update sglang_worker.py to fix #3372 error launching SGLand worker

vikrantrathore opened this pull request 7 months ago

Error in launching SGLang model worker multiple log values

vikrantrathore opened this issue 7 months ago

Can Azure openai GPT-4 work as judge?

don-tpanic opened this issue 7 months ago

add seed params support from vllm_worker

BuxianChen opened this pull request 7 months ago

Does it support Qwen1.5?

balala-s opened this issue 7 months ago

gguf

Jeffhop opened this issue 7 months ago

OpenAI API Streaming Issue Occurs with Error Code 50001

coolbeevip opened this issue 7 months ago

Incompatible OpenAI

coolbeevip opened this issue 7 months ago

fastchat.serve.model_worker --port 21003 and /v1/models show nothing

MarseusFu opened this issue 7 months ago

Update monitor.py

infwinston opened this pull request 7 months ago

spring ai的集成

cookiespiggy opened this issue 7 months ago

Support s3 paths for api-endpoint-file. Add ability to edit system prompt.

jonathanshen-upwork opened this pull request 7 months ago

Update time analysis

suquark opened this pull request 7 months ago

Feature: Add OpenAI Usage stats when using streaming with the Chat Completions API or Completions API

douxiaofeng99 opened this issue 7 months ago

Support for Phi-3 small and Phi-3 medium? Multimodal support?

coder543 opened this issue 7 months ago

[Bug] Single quote character `'` tripping up model generation and streaming

PyroGenesis opened this issue 7 months ago

Unable to use streaming with the /v1/embeddings API for the CodeQwen1.5-7B model.

fangx1129 opened this issue 7 months ago

[server] migrate pydantic from v1 to v2

NiuBlibing opened this pull request 7 months ago

Cannot use /v1/embeddings api with BGE-M3 model

chillizex opened this issue 7 months ago

[WIP] cleanup

suquark opened this pull request 7 months ago

New dataset release?

upintheairsheep opened this issue 7 months ago

Made it more clear that this data will be shared publicly.

upintheairsheep opened this pull request 7 months ago

Support using chat template in the tokenizer and use the generation config in model for vllm and openai endpoint

zeyugao opened this pull request 7 months ago

add script for de-duplication

infwinston opened this pull request 7 months ago

Update monitor.py

infwinston opened this pull request 7 months ago

Cannot succesfully pull VLMs to fastchat

PhilipAmadasun opened this issue 7 months ago

Error: Type object 'Dropdown' has no attribute 'update' in "qa_browser.py"

tanliboy opened this issue 7 months ago

Update gradio_web_server.py

lsy641 opened this pull request 7 months ago

moderate cannot be deactivated when running api-based model

lsy641 opened this issue 7 months ago

Update model_registry.py with GPT-4o

Mr-Twave opened this pull request 7 months ago

invalid openai api key when running "python3 -m fastchat.serve.openai_api_server --api-keys=[]"

lsy641 opened this issue 7 months ago

moderation_filter bug fix in fastchat/serve/gradio_block_arena_named.py

billy-inn opened this pull request 7 months ago

Misc changes for vision arena: change log, fix image moderation

BabyChouSr opened this pull request 7 months ago

Add UI changes

BabyChouSr opened this pull request 7 months ago

Added stars the vision arena

lisadunlap opened this pull request 7 months ago

Fix models with "llama-3" in the name and update Hermes adapter

teknium1 opened this pull request 7 months ago

Update vision arena docs and fix system for test

BabyChouSr opened this pull request 7 months ago

[refactor] Reorganize utils

suquark opened this pull request 7 months ago

support more LaTeX delimiters

kai01ai opened this pull request 7 months ago

Category Hard Data Labeling Script

CodingWithTim opened this pull request 7 months ago

火针

xiaogaowa opened this issue 7 months ago

feat: support system messages for DeepSeek-V2

congchan opened this pull request 7 months ago

The "Send" button is greyed out after pressing "New Round" on the Arena

Anixx opened this issue 7 months ago

update vllm_worker.py

jbding opened this pull request 7 months ago

Main

jbding opened this pull request 7 months ago

Vllm worker does not release semaphore

jbding opened this issue 7 months ago

Add CSAM and NSFW image moderation and fix Reka logging

BabyChouSr opened this pull request 7 months ago

Update inference.py

angelala00 opened this pull request 7 months ago

Can't get any available models via /v1/models

MarseusFu opened this issue 8 months ago

Support stream_options for openAI API

Binyang2014 opened this issue 8 months ago

python3 -m fastchat.serve.model_worker --model-path meta-llama/Meta-Llama-3-8B-Instruct got | ERROR | stderr | AssertionError

myrainbowandsky opened this issue 8 months ago

adding TenyxChat model and flows

matthew-ceravolo opened this pull request 8 months ago

Inquiry Regarding the Release of 1k MT-Bench Dataset

jerilkuriakose opened this issue 8 months ago

Using FastChat UI to Compare Multiple Local LLMs

soufianechami opened this issue 8 months ago

fix llama3 conversation format

Nero10578 opened this pull request 8 months ago

fix error and support Phi-3 models

renning22 opened this pull request 8 months ago

new release?

lnguyen opened this issue 8 months ago

How do you consider the 'top_k' parameter when using openai_api_server to start?

garyyang85 opened this issue 8 months ago

Merged Model from Huggingface runs fine with fastchat CLI but not when using service worker

heli-sdsu opened this issue 8 months ago

What is the system_message for llama3 model?

hahmad2008 opened this issue 8 months ago

Please add new model taide

keyang556 opened this issue 8 months ago

RayTokenizerGroupPool Adaptation?

Zephyr69 opened this issue 8 months ago

Leaderboard mentions `GPT-3.5-Turbo-0314` but I believe it is instead `GPT-3.5-Turbo-0301`

Franck-Dernoncourt opened this issue 8 months ago

how to fine-tune llama3?

meet-cjli opened this issue 8 months ago

Gpt2

12368w opened this issue 8 months ago

Opus and SVG

MartinPuda opened this issue 8 months ago

fastchat.serve.openai_api_server doesn't work with `stream=true` parameter

richginsberg opened this issue 8 months ago

problem gemini with Persian/Farsi language

Rahjooyan opened this issue 8 months ago

Update processing code

infwinston opened this pull request 8 months ago

Update monitor.py

infwinston opened this pull request 8 months ago

UI Improvements: unified link color, removed link underline, made window wider

lisadunlap opened this pull request 8 months ago

What's the version of gpt-4 of repo-provided ref answers

UbeCc opened this issue 8 months ago

Create and analyze statistics about the time it takes to vote

suquark opened this pull request 8 months ago