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.
in the example， I only find the fine-tuning with more than one GPUs. but I only have one GPU....
### problems encountered Although the current fastchat capability is very powerful, it still cannot obtain the current news, that is, the news of 2023 this year, and cannot realize the...
2023-04-18 10:42:03 | INFO | controller | args: Namespace(host='localhost', port=21001, dispatch_method='shortest_queue') 2023-04-18 10:42:03 | INFO | controller | Init controller 2023-04-18 10:42:03 | ERROR | stderr | INFO: Started server...
Hi Team, First of all I would like to say the model is very good in answering questions. Great work by the team. Just a suggestion if you can help...
FastChat/fastchat/serve/inference.py:132 in load_model NotImplementedError: Cannot copy out of meta tensor; no data!
try to run "python -m fastchat.model.apply_delta --base 7B --target output --delta vicuna-7b-delta-v0" but when"Applying delta" the error appeared “RuntimeError: The size of tensor a (32000) must match the size of...
Hello! During training, the data processing always reports the following error, what could be the reason?And what are the possible consequences? 
Instead of needing to load the weights into memory compare every byte in the LLaMA & Delta files and add the delta to the bytes, loading 4KB at a time,...
After training, I got **optimizer.pt pytorch_model.bin rng_state.pth scaler.pt scheduler.pt trainer_state.json training_args.bin** A model trained by train_lora.py does not give **config.json generation_config.json pytorch_model.bin.index.json**
Hi , i am tying to run Fastchat in cpu only mode , i and have the following error , any idea of what i need to do ? ``debian@srv-azrod:~$...
