FastChat
FastChat copied to clipboard
lm-sys
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Frequently, one of the results fails to generate. As seen in the screenshot, the left side failed to generate and there is no code, no error and no preview. It...
The sglang worker expects the is_multimodal_model from sglang's utility functions, but this has been removed since 0.3.5: ```python Traceback (most recent call last): File "/p/haicluster/llama/FastChat/fastchat/serve/sglang_worker.py", line 19, in from sglang.srt.utils...
Hi, Is it possible to access the text-to-image preference dataset with the generated images? Thanks
Please support this new model from LG AI Research to the Leaderboard, seems promising: https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-32B Thanks
Hi, we have our own LLM API. We would like to apply to join the Chatbot Arena (battle). We would greatly appreciate your kind response. Bests.
Are there any plans or is anyone working on integrating support for the Gemma 3 models within Fastchat? Natively loading a Gemma 3 model doesn't directly work and opens up...
## Why are these changes needed? ## Related issue number (if applicable) ## Checks - [x] I've run `format.sh` to lint the changes in this PR. - [x] I've included...
我用fastapi+transformers 启动了一个服务，在注册controller时，感觉是注册成功了，但获取worker状态报错 #worker_address:http://221.231.13.120:56908 # worker_name = "worker-221.231.13.120-56908" log: 2025-03-13 08:19:18 | INFO | controller | Register a new worker: worker-221.231.13.120-56908 2025-03-13 08:19:18 | ERROR | controller | Get status fails:...
A new version of vllm is available, which supports inference using bnb quantization. The properties of the vllm SamplingParams class have changed in the latest vllm version, but the fastchat...
