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.
NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE. (error_code: 50003, HTTPConnectionPool(host='localhost', port=21002): Read timed out.) 每次问第二个问题都会出现这个错误提示
More of a suggestion than an issue, but here's a gist describing what I did with the split_conversations.py script. https://gist.github.com/itsPat/a1bb06f1dfbd9d4b07288df3bb18b802 Improved it by making use of ijson, so that the...
when I use `python3 -m fastchat.serve.cli --model-path mpt-7b --load-8bit ` , it causes this error `ValueError: Tokenizer class GPTNeoXTokenizer does not exist or is not currently imported.`
Hi everyone: I want to run cacheflow_worker,but I can't found the way how to install cacheflow,where can i find this package? Can anyone guide me, thank you very much？
When using the langchain-chatGLM project to run, the model does not report an error and can be used normally, but when it is changed to FastChat, the following error appears....
Hi, i launch a worker with python3 -m fastchat.serve.model_worker --model-path /home/llamaweights/vicuna-13b --device cpu and then the webGUI, which works fine so far. When i do a request, after an initial...
ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as `pad_token` `(tokenizer.pad_token = tokenizer.eos_token e.g.)` or add a new pad...
I use 1 node with 4*V100，got 700it/s，and 1 node with 4*P40，got 300it/s， but when I use 2 nodes with 4*V100 and 4*P40 by deepspeed，got **“4 pytorch allocator cache flushes since...
Getting this error: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models/. cmd: python3 -m fastchat.serve.cli --model-path models/ --num-gpus 4
Hi! I would like to know if the conversation templates can be changed. I am using two models T5 and vicuna-7b. The default T5 conversation template is long and reduces...
