base_model: universeTBD/astrollama-7b-alpha
tags:
- generated_from_trainer
datasets:
- customized
model-index:
- name: astrollama-7b-chat-alpha
results: []
AstroLLaMA Chat
Check out the model in our Hugging Face space!
universeTBD/astrollama-7b-chat-alpha
Model description
This model is a fine-tuned version of universeTBD/astrollama-7b-alpha on a mix of various open-source conversational datasets, as specified in our research note.
The underlying model of AstroLLaMA 7B Alpha is Llama 2 7B, which has been trained using 300k arXiv astro-ph abstracts, introductions, and conclusions. For more information, please refer to the research note.
Intended uses & limitations
With the release of this alpha model, we hope to inspire more astronomers to explore the fine tuning of smaller models.
Please be advised, that the alpha version of our model may not be perfect and robust. At times, it might generate strange or confusing outputs. As this is an alpha version, it has not been aligned with safety guidelines, making it potentially susceptible to misuse.
Model usage
To achieve the desired features and performance from the chat model, it is essential to adhere to a specific formatting, which is the following: ###Human: {content}, ###Assistant: {content}.