Instructions to use berkeley-nest/Starling-RM-7B-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use berkeley-nest/Starling-RM-7B-alpha with Transformers:
# Load model directly from transformers import AutoTokenizer, LLMForSequenceRegression tokenizer = AutoTokenizer.from_pretrained("berkeley-nest/Starling-RM-7B-alpha") model = LLMForSequenceRegression.from_pretrained("berkeley-nest/Starling-RM-7B-alpha") - Notebooks
- Google Colab
- Kaggle
Any ETA on your paper?
#7
by ttkciar - opened
I am a huge fan of the Starling models and of RLAIF. Your various READMEs and your blog post give tantalizing clues as to your methods and processes, but there is still a lot missing from them.
Doubtless many of us in the LLM R&D community are waiting anxiously for you to publish your paper, for a more complete description of your methods. Do you have any idea of when you might have a preprint published to arXiv?
ttkciar changed discussion status to closed
Thank you! We're working to get the paper out soon in several weeks. The one you sent is not the paper for starling.