kashifr

Recent Submissions

1. 1. ▲ Distilling 100B+ Models 40x Faster with TRL (huggingface.co) 12 points · 2 days ago · 0 comments
2. 2. ▲ Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries (huggingface.co) 2 points · 1 month ago · 0 comments
3. 3. ▲ Transformers V5 is out! (github.com) 10 points · 2 months ago · 0 comments
4. 4. ▲ The Smol Training Playbook: The Secrets to Building World-Class LLMs (huggingface.co) 265 points · 5 months ago · 19 comments
5. 5. ▲ Unlocking On-Policy Distillation for Any Model Family (huggingface.co) 6 points · 5 months ago · 1 comment
6. 6. ▲ Transformers 4.55 New OpenAI GPT OSS (github.com) 2 points · 8 months ago · 1 comment
7. 7. ▲ Smollm3: Smol, multilingual, long-context reasoner LLM (huggingface.co) 388 points · 9 months ago · 79 comments
8. 8. ▲ Epic vs. Apple (twitter.com) 7 points · 11 months ago · 0 comments
9. 9. ▲ AIMO (AI Math Olympiad) progress prize winning solution (huggingface.co) 9 points · 1 year ago · 0 comments
10. 10. ▲ MaPO: A reference-free alignment technique for diffusion models (mapo-t2i.github.io) 2 points · 1 year ago · 1 comment