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.
python3: Error while finding module specification for 'fastchat.model.apply_delta' (ModuleNotFoundError: No module named 'fastchat.model') any idea? thanks. env :python3.9, macOS12.5.1 (21G83) M1
Would this be suitable as the base model https://huggingface.co/cerebras/Cerebras-GPT-13B seems to be free of any licensing limitations
Hi, in the function `def generate_stream` in `inference.py`, the attention mask setup as: ``` attention_mask = torch.ones( 1, past_key_values[0][0].shape[-2] + 1, device=device) ``` It seems that the attention mask shape...
such as --question-file tables/question.jsonl, how to generate question.jsonl
I am trying to follow the instructions it says 2 methods. If for inference python package is there then do rest of the steps still apply. Any example would be...
Hello folks, I'm strugling to install fastchat, it seems to fail to install sentencepiece. Any help appreciated! ``` C:\chat\FastChat>pip list Package Version ---------- ------- pip 23.0.1 setuptools 65.5.0 tokenizers 0.13.3...
When I ask the model to generate html code, it parshes the code and do not show code directly.
For OpenAI API, they provide both Completion and Embedding API. And they claimed that text embedding was [trained by Contrastive Pre-Training](https://arxiv.org/abs/2201.10005). Now LLaMA/Vicuna have basically replicated the function of OpenAI's...
I'm not sure if langchain support is already possible with this model, but if it isn't, I would like to request that it be implemented. If it is already possible,...
