Update README.md

Update README.md

Update README.md

Update README.md

Update train.py

Update README.md

Delete mock_worker.py

Update train.py

Upload MODEL_CARD.md

Update BLOG.md

Create BLOG.md

Update README.md

Update README.md

Update train.py

Fix: Use Level 1 scenarios only for training

Add MemoryLedger

Add WorldModelSimulator

Training script with WorldModel/Memory integration

Update README with all required links

Add OpenEnv manifest

More SFT warmup (40 steps) for better JSON format

Added friend laptop worker via ngrok

Added friend worker + local worker dispatch

Updated: 250 steps, K=2, LR=1e-5, temp 1.0-0.7

Add worker setup guide

Add mock worker for demo

Add worker client with local ngrok URL

train: higher LR=1e-5, more SFT=20, lower temp=1.0->0.7

chore: remove binary artifacts from git

faster training: lower temp, higher LR, more SFT

Upload Dockerfile with huggingface_hub

Upload Dockerfile with huggingface_hub

Upload Dockerfile with huggingface_hub

Upload train.py with huggingface_hub

Upload Dockerfile with huggingface_hub

Upload folder using huggingface_hub

fix: C-4 reward clamp, C-6 HF_TOKEN, W-2 citation floor, W-9 dup import

fix: force torch 2.5.1+cu121 after unsloth to prevent colab-new downgrade

fix: upgrade PyTorch to 2.5.1 to fix unsloth_zoo AttributeError on torch._inductor.config

Upload Dockerfile with huggingface_hub

Upload hf_training/train.py with huggingface_hub

Upload Dockerfile with huggingface_hub

Upload README.md with huggingface_hub

Upload folder using huggingface_hub

Upload README.md with huggingface_hub

Upload Dockerfile with huggingface_hub

Upload folder using huggingface_hub

Upload Dockerfile with huggingface_hub

Upload train.py with huggingface_hub

Upload folder using huggingface_hub