PhysicsWallahAI
/

Aryabhata-1.0

Text Generation

small-language-model

indian-education

reinforcement-learning

supervised-finetuning

rejection-sampling

text-generation-inference

Model card Files Files and versions

Resources

View closed (6)

Discrepency with tokenizer that causes model to never terminate by itself

#10 opened 3 days ago by

Add link to GitHub repository

#9 opened 22 days ago by

Aligning Reward Model with Competitive Exam Marking Schemes ( JEE mains for Aryabhata-1.0 )

#7 opened about 1 month ago by