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.
## Why are these changes needed? Adds Claude 3.5 Sonnet to the arena. I didn't edit conversation.py, should I? Possible (long!) system prompt: https://gist.github.com/Richard-Weiss/825ade67b9dce6df5537d926925b7745 ## Related issue number (if applicable)...
https://huggingface.co/EleutherAI/gpt-j-6b Outdated, but it would be good to add.
## Why are these changes needed? This PR addresses a potential issue in the `api_generate_stream` function where the semaphore might not be properly released in all scenarios. Specifically, if an...
I have deployed mistral7b and 8x&B models in two AWS EC2 server using vllm and fstchat , and now I want to communicate through a web interface(gradio_webserver) and i am...
Hi! I'm building my own LLM, and I would like to serve it with FastChat. My idea is to deploy the Gradio App on AWS or GCP, and run the...
I would like to adapt GLM4 to FastChat in order to leverage FastChat's features for deploying and testing the conversation model.I am working on adapting GLM4 to FastChat, but I...
I used the following command to generate Vicuna, but the following error occurred. Which step did I do wrong? python3 -m fastchat.model.apply_delta \ --base-model-path /path/to/llama-7b \ --target-model-path /path/to/output/vicuna-7b \ --delta-path...
I saw chatbot areana had the multimodal version. Could we add 72B/110B LLaVA-Next model to it? Or we already had it? We really wish to see the performance on real...
## Why are these changes needed? Fix the issue of semaphore unreleased due to internal exception ## Related issue number (if applicable) ## Checks - [ ] I've run `format.sh`...
Hi, I am new to this area. Nice work of FastChat! I am thinking of using knowledge graph for RAG to enhance the capability of FastChat chatBot. Any support or...
