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.
Can anybody reproduce this problem? Direct Chat with Opus -> "draw SVG image of..." / "generate SVG code of..." freezes the whole page and hides the output for this prompt....
I'm trying to get FastChat working on https://github.com/open-webui/open-webui via it's option to accept OpenAI compatible endpoints. TabbyAPI seems to be able to serve OpenAI API format with streaming/chunking. FastChat doesn't...
hi, I can't use gemini AI for Persian/Farsi language but I don't have problem with other languages like Arabic. Please fix this problem. ``` API REQUEST ERROR Reason: index: 0...
## Why are these changes needed? ## Related issue number (if applicable) ## Checks - [ ] I've run `format.sh` to lint the changes in this PR. - [ ]...
This code, https://github.com/lm-sys/FastChat/blob/d04ce6453ae016d9e03626b679c07aa1388dcbee/fastchat/serve/controller.py#L175, is unreachable. Is that expected?
For anyone that has gotten VLMs to work in fastchat. How did you do so? I cannot even pull any llava model from hugging face successfully. These have been my...
Hi FastChat team, I ran into this error while starting the qa broswer. It seems that the Dropdown::update has been removed (https://github.com/gradio-app/gradio/issues/6862), and we need update the qa_browser.py. Or did...
When I use the Qwen2 series of models for inference in Ascend 910B 。 There are some things that are not normal When I set the top_p = 1.0, it...
Change log to separate data that has been flagged.
bug fix: do moderation_filter only if do_moderation == True ## Why are these changes needed? ## Related issue number (if applicable) ## Checks - [x] I've run `format.sh` to lint...
