| user: | kashifr |
| created: | March 11, 2011 |
| karma: | 750 |
| about: | https://github.com/kashif https://twitter.com/krasul |
| 1. | |
| 2. | Distilling 100B+ Models 40x Faster with TRL(huggingface.co) |
| 3. | |
| 4. | Transformers V5 is out!(github.com) |
| 5. | |
| 6. | Unlocking On-Policy Distillation for Any Model Family(huggingface.co) |
| 7. | Transformers 4.55 New OpenAI GPT OSS(github.com) |
| 8. | Smollm3: Smol, multilingual, long-context reasoner LLM(huggingface.co) |
| 9. | Epic vs. Apple(twitter.com) |
| 10. | AIMO (AI Math Olympiad) progress prize winning solution(huggingface.co) |
| 11. | MaPO: A reference-free alignment technique for diffusion models(mapo-t2i.github.io) |
| 12. | |
| 13. | HuggingFace Training Cluster as a Service(huggingface.co) |
| 14. | HuggingFace 235M series D at a $4.5B valuation(twitter.com) |
| 15. | Fine-tune Llama 2 with DPO(huggingface.co) |
| 16. | QLoRA 4-bit finetuning of LLMs(github.com) |
| 17. | StackLlama: A hands-on guide to train LlaMa with RLHF(huggingface.co) |
| 18. | |
| 19. | |
| 20. | Generic Neural Elastic Search(gnes.ai) |