Lemur πŸ¦₯

Lemur is a chatbot model based on the LLaMA model, further fine-tuned using LoRA on several openly available datasets (Alpaca-GPT4, Baize, ShareGPT and Vicuna-Dummy-Conversation).

Note: Lemur is specifically designed and trained for the exclusive purpose of our final project for CSE 256 Statistical Natural Lang Processing at UCSD. It is not intended for any commercial usage or widespread deployment. Testing and exploration are permitted, but we request that you limit your use to this purpose only. Please respect these guidelines to maintain the integrity of our project and its intended use.

Warning: The usage of ShareGPT data might pose copyright issues, which are currently under dispute. If you are considering the use of this model, we strongly advise you to proceed with caution.

Demo on πŸ€— Huggingface Space

https://huggingface.co/spaces/tianyang/lemur-7B

It is running on a 16GB CPU (free πŸ€— Huggingface Spaces), with really slow inferecing speed. (~30s for processing a single question, and ~1s per subsequent token)

Format

MSG = Hi, how are you?

prompt = f"""A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
[Human]: {MSG}
[AI]:"""

Notice

Lemur is specifically designed and trained for the exclusive purpose of our final project. It is not intended for commercial usage or widespread deployment. Testing and exploration are permitted, but we request that you limit your use to this purpose only. Please respect these guidelines to maintain the integrity of our project and its intended use.

Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using tianyang/lemur-7B 1