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.
First of all, thank you for opening up such a great project. I had a great experience with 13B. When can I deploy a model with larger parameters?
https://github.com/FreedomIntelligence/LLMZoo looks also interesting for ELO compare ;) weight could be downloaded from https://github.com/FreedomIntelligence/LLMZoo#phoenix-llm-across-languages
Is the api inference available for t5. Any example available? Also what's the format of data.
Thanks for your great job! I have checked the code of v0 and v1, and found some differences between the prompts: ```python # Vicuna-v0 sep = "###" train_prompt = "system.###...
I am pleased to submit a pull request to support the token usage field in the ChatGPT-compatible Restful API. The "chat_completion" function in "api.py" has been modified to return a...
When running fine-tuning command on a single machine with a single network adapter, init_process_group is called and there is no response for a long time, which seems to be hanged....
My friend in China is trying to access the chatbot website I deployed on our own server. He got **connection timeout error**. I increased the timeout parameter to 50 and...
Adding support for stream for `ChatCompletion` in the client and in the API. ## How to use? ### Async ```python from fastchat import client async def async_main(): model_name = "vicuna-7b"...
1. Environments: * Windows 11 * Python 3.10.6 * Pytorch 2.0.0+cu118 * Gradio WebUI 2. Steps to produce: * `python3 -m fastchat.serve.controller` * `python3 -m fastchat.serve.model_worker --load-8bit --model-path .\vicuna_13b\` 3....
Address https://github.com/lm-sys/FastChat/issues/350 Verification: controller ``` 2023-05-05 00:51:45 | INFO | gradio_web_server | ==== request ==== {'model': 'vicuna-13b', 'prompt': "A chat between a curious user and an artificial intelligence assistant. The...
