Spaces:
Runtime error
Runtime error
Commit History
-
Update README.md
Verified signature3acf10b -
Update README.md
Verified signaturee3603dc -
Update README.md
Verified signaturecb6a4ca -
Update README.md
Verified signatureadd766c -
Update train.py
Verified signaturef3fc038 -
Update README.md
Verified signature3c7a3a5 -
Delete mock_worker.py
Verified signatureaa1d7f7 -
Update train.py
Verified signature6a2dd66 -
Upload MODEL_CARD.md
Verified signature5d8f1e9 -
Update BLOG.md
Verified signature1f65562 -
Create BLOG.md
Verified signature767ffe9 -
Update README.md
Verified signature904779b -
Update README.md
Verified signature926997e -
Update train.py
Verified signaturef330c3f -
Fix: Use Level 1 scenarios only for training
Verified signature7a19964 -
Add MemoryLedger
Verified signature9a90a52 -
Add WorldModelSimulator
Verified signature2327c5a -
Training script with WorldModel/Memory integration
Verified signature48a7cf6 -
Update README with all required links
Verified signature1a5a502 -
Add OpenEnv manifest
Verified signature609a677 -
More SFT warmup (40 steps) for better JSON format
Verified signatureaac0ab9 -
Added friend laptop worker via ngrok
Verified signature2688686 -
Added friend worker + local worker dispatch
Verified signature07656ee -
Updated: 250 steps, K=2, LR=1e-5, temp 1.0-0.7
Verified signaturea0297c3 -
Add worker setup guide
Verified signature7275c33 -
Add mock worker for demo
Verified signature7bffd13 -
Add worker client with local ngrok URL
Verified signatureedc3562 -
train: higher LR=1e-5, more SFT=20, lower temp=1.0->0.7
23c3a1b -
chore: remove binary artifacts from git
5e5d438 -
faster training: lower temp, higher LR, more SFT
Verified signaturec84d93d -
Upload Dockerfile with huggingface_hub
Verified signature31fe512 -
Upload Dockerfile with huggingface_hub
Verified signature524f673 -
Upload Dockerfile with huggingface_hub
Verified signaturef5ca8fb -
Upload train.py with huggingface_hub
Verified signaturee5115bd -
Upload Dockerfile with huggingface_hub
Verified signatureda61617 -
Upload folder using huggingface_hub
Verified signature8b092ea -
fix: C-4 reward clamp, C-6 HF_TOKEN, W-2 citation floor, W-9 dup import
Verified signatureb022bda -
fix: force torch 2.5.1+cu121 after unsloth to prevent colab-new downgrade
Verified signature9e1ad05 -
fix: upgrade PyTorch to 2.5.1 to fix unsloth_zoo AttributeError on torch._inductor.config
Verified signatureff9091d -
Upload Dockerfile with huggingface_hub
Verified signaturece8daf0 -
Upload hf_training/train.py with huggingface_hub
Verified signaturec51cef7 -
Upload Dockerfile with huggingface_hub
Verified signature4981837 -
Upload README.md with huggingface_hub
Verified signature85a478c -
Upload folder using huggingface_hub
Verified signature206f794 -
Upload README.md with huggingface_hub
Verified signatureacb482d -
Upload Dockerfile with huggingface_hub
Verified signature319ef7e -
Upload folder using huggingface_hub
Verified signaturee945ec1 -
Upload Dockerfile with huggingface_hub
Verified signature854a3f5 -
Upload train.py with huggingface_hub
Verified signature466a284 -
Upload folder using huggingface_hub
Verified signature51db3e8