Instructions to use limmin33/opd-rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use limmin33/opd-rl with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("limmin33/opd-rl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Archive SDAR checkpoint global_step_150
Verified signaturec882a14 -
Archive SDAR checkpoint global_step_135
Verified signatured6f1f95 -
Archive SDAR checkpoint global_step_120
Verified signature61b5a89 -
Archive SDAR checkpoint global_step_105
Verified signature0202aba -
Archive SDAR checkpoint global_step_90
Verified signature0f9c6d7 -
Archive SDAR checkpoint global_step_75
Verified signature1169d5a -
Archive SDAR checkpoint global_step_60
Verified signature4dffdeb -
Archive SDAR checkpoint global_step_45
Verified signaturefc49abf -
Archive SDAR checkpoint global_step_30
Verified signaturebe5ec55 -
Archive SDAR checkpoint global_step_15
Verified signaturedc5bf95
-
Document environment/model/method/checkpoint layout
Verified signaturec2efb5b -
Add alfworld/qwen3-1.7b/sdar_coef0.01_beta5.0_skillallfalse/global_step_150
Verified signature57c7fed -
Add alfworld/qwen3-1.7b/sdar_coef0.01_beta5.0_skillallfalse/global_step_100
Verified signaturee669a18 -
Add alfworld/qwen3-1.7b/sdar_coef0.01_beta5.0_skillallfalse/global_step_50
Verified signaturea0ab6c0 -
Add alfworld/qwen3-1.7b/rlsd_warmdown_100/global_step_150
Verified signature8ae6ca5 -
Add alfworld/qwen3-1.7b/rlsd_warmdown_100/global_step_100
Verified signature855ab7f -
Add alfworld/qwen3-1.7b/rlsd_warmdown_100/global_step_50
Verified signature62b3688 -
Add alfworld/qwen2.5-3b/rlsd_warmdown_100/global_step_150
Verified signature263b744 -
Add alfworld/qwen3-1.7b/grpo_2gpu/global_step_150
Verified signatured810b3f -
Add alfworld/qwen3-1.7b/grpo_2gpu/global_step_100
Verified signature41cdb8a -
Add alfworld/qwen3-1.7b/grpo_2gpu/global_step_50
Verified signaturee87bbbb -
Add alfworld/qwen2.5-3b/grpo/global_step_50
Verified signature1d7d723 -
Move sdar_qwen2.5_3b_alfworld to alfworld/qwen2.5-3b/sdar_coef0.01_beta5.0_skillallfalse
Verified signature3a1990a
-
SDAR Qwen2.5-3B-Instruct ALFWorld, step 150 checkpoint (FSDP shards, world_size=2)
Verified signaturec42752e -
initial commit
Verified signature77e316d