trl-lib on Hugging Face: model downloads

trl-lib has 21 tracked models, downloaded 1,801 times in the last 30 days and 109,796 times in total. trl-lib Wrapped: the last 12 months.

Models by downloads in the last 30 days

  1. trl-lib/pythia-1b-deduped-tldr-sft 1.2K downloads, model
  2. trl-lib/Qwen2-0.5B-Reward 199 downloads, text classification
  3. trl-lib/qwen1.5-0.5b-sft 95 downloads, text generation
  4. trl-lib/pythia-2.8b-deduped-tldr-sft 81 downloads, model
  5. trl-lib/pythia-1b-deduped-tldr-rm 38 downloads, model
  6. trl-lib/Qwen2-0.5B-Reward-Math-Sheperd 32 downloads, token classification
  7. trl-lib/Qwen2-0.5B-OnlineDPO 27 downloads, text generation
  8. trl-lib/Qwen2-0.5B-XPO 25 downloads, text generation
  9. trl-lib/qwen1.5-1.8b-sft 24 downloads, text generation
  10. trl-lib/Qwen2-0.5B-DPO 18 downloads, text generation
  11. trl-lib/Qwen2-0.5B-ORPO 17 downloads, text generation
  12. trl-lib/Qwen2-0.5B-KTO 17 downloads, text generation
  13. trl-lib/pythia-6.9b-deduped-tldr-sft 11 downloads, model
  14. trl-lib/pythia-6.9b-deduped-tldr-rm 8 downloads, model
  15. trl-lib/pythia-2.8b-deduped-tldr-rm 7 downloads, model
  16. trl-lib/ddpo-aesthetic-predictor 0 downloads, model
  17. trl-lib/llama-7b-hh-rm-adapter 0 downloads, model
  18. trl-lib/llama-7b-se-rl-peft 0 downloads, model
  19. trl-lib/llama-7b-se-rm-peft 0 downloads, model
  20. trl-lib/Qwen3-4B-LoRA 0 downloads, model
  21. trl-lib/llama-7b-se-peft 0 downloads, model