This modelcard aims to be a base template for new models. It has been generated using this raw template.
Model Details
Model Description
Trained at 16384 context length to summarize articles from arxiv-summarization dataset. Fine tuning was run using QLoRA techniques to limit memory usage while targetting as many layers as possible.
Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]
Uses
Use for simple article summarization tasks:
summarize:
[article]
summary:
...
Direct Use
TODO
Out-of-Scope Use
Not a regular instruction model. Tasks other than summarizations may not work as expected.
Bias, Risks, and Limitations
TODO
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
