OctoThinker

/

Llama3.2-3B-Zero

like 0

Follow

OctoThinker 32

This PR adds a model card by linking it to the paper OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling.
It also adds the library_name: transformers and pipeline_tag: text-generation to the model card.
It also adds a link to the project page.