Text Classification
Transformers
Safetensors
Laya
system-one
calibrated-decisions
rlcd
classification
routing
scoring
guardrails
moderation
reinforcement-learning
commercial-use
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
Higher-Context
#17
by amarosnithe - opened
Congratulations to the development team, this is genuinely life-changing and you're clearly making history. The only criticism/suggestion I personally have is that there should be a bigger context-length (512 feels too small, decent for most tasks but not enough for bigger data/documents). If anyone can do a Laya that has like, 32k of context minimum, then you're literally asking for World Domination with this shit. The amount of potential with it is limitless.
Multilingual model supports up to 8k
I might be wrong but I feel like 8 is smaller than 32.. I think.