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.
When using Tor Browser to access [lmarena.ai](https://lmarena.ai), I encounter recurring errors that prevent normal operation. Often, the text input field does not load with the message `error Connection errored out.`...
Gradio 5 has come out. It has two things which are interesting: - It's much faster, - It has a resizable chatbot field. However, a lot of things changed in...
## Why are these changes needed? An error occurs when starting gradio_web_server_multi because the wheel package does not contain images under fastchat/serve/example_images/. Modify pyproject.toml to include this directory in the...
## Why are these changes needed? lllama 3.1 conversation template is not right. See Issue #3547 Closes: #3547
Hi! I encountered an unusual visual issue in the **🏆 Chatbot Arena LLM Leaderboard** section at [https://lmarena.ai/](https://lmarena.ai/). When scrolling or interacting with the leaderboard (e.g., hovering over entries or rankings),...
@CodingWithTim ## 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...
Add support for conversation with phi-4. I don't have the hallucination about the birthday party of the default conversation anymore. Since I'm not a llm expert, someone used to add...
current behaviour: auto scroll looks cool but is an anti-feature, it wastes a lot of time in waiting for it to finish and then scrolling back to read the answer....
## Description: I followed the instructions to run the WebGUI service in single-model mode by launching the controller, model workers, and Gradio web server. However, when I opened the website,...
Describe the issue "I have locally deployed bge-large-zh-v1.5 + qwen2.5-3B-Instruct + GraphRAG 1.1.2, using Python 3.10.12 and torch 2.5. When I run the graphrag index --root ./ command, I encounter...
