Nathan T. Foster

punesharma

4 4

·

AI & ML interests

Love fine-tuning models and sharing datasets.

Recent Activity

updated a model 6 days ago

punesharma/document-ai-finetune

published a model 6 days ago

punesharma/document-ai-finetune

upvoted a paper 6 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

View all activity

Organizations

None yet

models 4

punesharma/document-ai-finetune

33.1k • Updated 6 days ago • 8

punesharma/generation-weights

49.6k • Updated 24 days ago • 23

punesharma/whisper-retrieval

punesharma/paper_013515290_multimodal_reasoning

datasets 0

None public yet