FastChat
FastChat copied to clipboard
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Hello, may you please collaborate with xAI to get unlimited API access to Grok-1 (similar to how you got access to the updated GPT-4 and GPT-4o (Omni) before it was...
I've been examining the `api_generate_stream` function in the `fastchat/serve/vllm_worker.py` file and I've noticed a potential issue related to the semaphore release. In the current implementation, if an exception occurs during...
I used the latest code to test the mt bench score of llama-2-chat, and the test result was only about 5.86. However, the official data provided was as high as...
Dear all, Thank you for your amazing works. I would like to build an arena that for specific tasks. Could I get the exact code of chat.lmsys.org and I can...
 我认为是我在执行这条命令的时候出现了错误`python3 -m fastchat.serve.model_worker --model-path THUDM/chatglm3-6b --model-names chatglm3-6b`,因为这条命令默认`--conv-template vicuna_v1.1`,而我的模型并非vicuna
## Why are these changes needed? Update time analysis: * 30x faster data processing * consider judge time normalized by number of chars * more plots * filter votes by...
Our LLM model is on endpoint : # from langchain.indexes import VectorstoreIndexCreator os.environ["OPENAI_API_BASE"] = "my_endpoint_ip" os.environ["OPENAI_API_KEY"] = "empty" embedding = OpenAIEmbeddings(model="text-embedding-ada-002") local_llm = OpenAI(model="gpt-3.5-turbo") So while performing below retrieval task...
Hello lm-sys team, I was looking through the code base of Fastchat for Chatbot arena code but I Couldn't find it. I am specifically interested on the model selection when...
I found that typing enter into the textbox would wrap lines and typing shift + enter would commit. I want to swap these two functions, commit with enter and wrap...
We hope make our LLM named BaiLing become the one of the optional LLM on the chat.lmsys.org and join the chat on the website. We setup our own http end-point...