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.
I noticed multiple languages are supported in the Arena and I'm interested to add support to Arabic as well. But i have no idea where to start ! Can you...
Hello, I am wondering how to do best-of-n sampling in MT bench. Is this something implemented somewhere? Thanks!
Hello - I notice that the chat arena version of fastchat-t5-3b-v1.0 provides quite different answers from the model compared to when it is downloaded manually and run using fastchat.serve.cli --model-path...
## Why are these changes needed? - AML support - AOAI endpoint - Phi2 model eval ## Related issue number (if applicable) ## Checks - [ ] I've run `format.sh`...
Every model I try ends up with a similar error. This, specifically, is Vicuna-13 from https://huggingface.co/4bit/vicuna-13b-GPTQ-4bit-128g Those are the options I used for calling it: ``` python3 $BLABLADOR_DIR/fastchat/serve/model_worker.py \ --controller...
I am using the qwen 72B model, and the specified --conv-template does not take effect. If the stop parameter is not specified when calling, the conversation will never end. 启动命令...
## Why are these changes needed? This change adds a preamble with the current date, giving the Cohere model necessary temporal context. ## Related issue number (if applicable) ## Checks...
If i use cpu i got the error that [intel-extension-for-pytorch](https://github.com/intel/intel-extension-for-pytorch) is missing If i use xpu i got this error ``` 2024-03-14 06:15:45 2024-03-14 05:15:45 | INFO | model_worker |...
Dear maintainers, Thank you for your valuable arena. I am currently researching the way of LLMs evaluation and got stack with a question about Bradley-Terry model. As it stands, from...
