RLLab AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
14
Downloads 30D
1,680
Total downloads
6,912
Total likes
0
Gained 7D
11

Most downloaded

  1. 1olmo-3-1025-7bSep 22, 2026426
  2. 2olmo-3-7b-it-sftSep 29, 2026342
  3. 3gemma-3-4b-text-itSep 13, 2026320
  4. 4qwen3-4b-base-lr-1e-6-gdpo-len8k-step120Sep 29, 2026198
  5. 5qwen3-4b-base-lr-1e-6-gdpo-len8k-step200Sep 29, 2026198
  6. 6qwen3-4b-safe-alignment-helpfulSep 11, 202656
  7. 7qwen3-4b-safe-alignment-harmlessSep 11, 202650
  8. 8qwen2.5-3b-safe-alignmentSep 11, 202634
  9. 9Qwen2.5-7B-SafeRLHF-RMJul 1, 202623
  10. 10olmo-3-7b-it-sft-lr-1e-6-gdpo-len8k-gatew1.0Oct 5, 202620

Fastest growing

  1. 1gemma-3-4b-text-it+0 in 7D320

Recently updated

  1. 1olmo-3-7b-it-sft-lr-1e-6-gdpo-len8k-gatew1.0Oct 5, 202620
  2. 2qwen3-4b-base-lr-1e-6-gdpo-len8k-step200Sep 29, 2026198
  3. 3qwen3-4b-base-lr-1e-6-gdpo-len8k-step120Sep 29, 2026198
  4. 4olmo-3-7b-it-sftSep 29, 2026342
  5. 5olmo-3-1025-7bSep 22, 2026426
  6. 6gemma-3-4b-text-itSep 13, 2026320
  7. 7qwen2.5-3b-safe-alignmentSep 11, 202634
  8. 8qwen3-4b-safe-alignment-harmlessSep 11, 202650
  9. 9qwen3-4b-safe-alignment-helpfulSep 11, 202656
  10. 10qwen3-4b-safe-alignment-sftSep 7, 20260

All models

All tracked models published by RLLab
ModelDL 30D7D
olmo-3-1025-7brllab/olmo-3-1025-7b426—
olmo-3-7b-it-sftrllab/olmo-3-7b-it-sft342—
gemma-3-4b-text-itrllab/gemma-3-4b-text-it320+0
qwen3-4b-base-lr-1e-6-gdpo-len8k-step120rllab/qwen3-4b-base-lr-1e-6-gdpo-len8k-step120198—
qwen3-4b-base-lr-1e-6-gdpo-len8k-step200rllab/qwen3-4b-base-lr-1e-6-gdpo-len8k-step200198—
qwen3-4b-safe-alignment-helpfulrllab/qwen3-4b-safe-alignment-helpful56+0
qwen3-4b-safe-alignment-harmlessrllab/qwen3-4b-safe-alignment-harmless50+0
qwen2.5-3b-safe-alignmentrllab/qwen2.5-3b-safe-alignment34+0
Qwen2.5-7B-SafeRLHF-RMrllab/qwen2.5-7b-saferlhf-rm23+7
olmo-3-7b-it-sft-lr-1e-6-gdpo-len8k-gatew1.0rllab/olmo-3-7b-it-sft-lr-1e-6-gdpo-len8k-gatew1.020—
Qwen2.5-7B-SafeRLHF-CMrllab/qwen2.5-7b-saferlhf-cm12+4
qwen3-1.7b-safe-alignment-sftrllab/qwen3-1.7b-safe-alignment-sft0+0
qwen3-4b-safe-alignment-sftrllab/qwen3-4b-safe-alignment-sft0+0
deepseek-r1-distill-qwen-1.5b-adam-lr-1e-6-vanilla-geoma-step-60rllab/deepseek-r1-distill-qwen-1.5b-adam-lr-1e-6-vanilla-geoma-step-600+0