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? I want to quickly find the best models with open weights. ## Related issue number (if applicable) Closes #3614 ## Checks - [x] I've...
How do I deploy the InternVL2_5-78B model using the fastchat framework?
## Why are these changes needed? Current intended links ## Related issue number (if applicable) ## Checks - [ ] I've run `format.sh` to lint the changes in this PR....
## Issue: Misleading "Too many requests" error during first-time login **Disclaimer:** this issue text was improved with Chatbot arena. ### Current Behavior When attempting to sign in for the first...
Hi there, I wonder if it is possible to use a local or open model as a judge instead of GPT-4, e.g., deploying it via vllm. Best.
Hello, recently I've tried to fine-tune vicuna with train_lora.py and encounterd some error I failed to resolve. I try the following script ```shell deepspeed $CODE_PATH \ --model_name_or_path $MODEL_PATH \ --lora_r...
On Lmsys arena, I am trying to upload this image:  When I upload it, it appears on the left side of the screen but not on the right side...
 生成的长度与设置的值保持了一致，这种情况怎么解决呢？
## Why are these changes needed? When deploying inference services with ASCEND NPU, it is not possible to specify the card to be used. @infwinston @CodingWithTim ## Related issue number...
