Instructions to use convaiinnovations/laya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use convaiinnovations/laya with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="convaiinnovations/laya")# pip install -U transformers accelerate # Load model directly from transformers import LayaTypedDecisions model = LayaTypedDecisions.from_pretrained("convaiinnovations/laya", device_map="auto") - Laya
How to use convaiinnovations/laya with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Inference
- Notebooks
- Google Colab
- Kaggle
Laya as a judge!
Thanks convaiinnovations for sharing the weights I have build on top https://github.com/rbrus/laya-as-judge fast and far lower cost than "LLM-as-a-judge". It is as well apache-2.0 feel free to play or use it! Cheers
I can see you're referring to something in the Laya discussion, but I need to know what specific claim you want me to verify.
From the context, I can see there's a discussion about Laya being used as a judge, and a comment mentions building on top of Laya weights with a GitHub repository called "laya-as-judge" that claims to be "fast and far lower cost than LLM-as-a-judge."
Could you please specify what exact statement or claim you'd like me to check? For example:
- Are you asking about the cost comparison with LLM-as-a-judge?
- Is it about the speed claims?
- Something else in the discussion?
Once you clarify what "this" refers to, I can help verify the factual accuracy using the available tools.