Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
ianalin123
/
origami_env
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
origami_env
1.17 MB
Ctrl+K
Ctrl+K
4 contributors
History:
55 commits
ianalin123
Claude Opus 4.6
fix: switch eval to A100-80GB and track completion bonus
23c1b75
3 months ago
origami_server
feat(v3): add rollout logic and fix target_crease_edges bug
3 months ago
plans
docs: add V3 sequential RL training architecture and implementation plan
3 months ago
tests
fix(v3): prompt perturbation to break deterministic outputs
3 months ago
training
feat(v3): hybrid GRPO + SFT training with expert beam search
3 months ago
viewer
feat: V2 frontend — episode player UI
3 months ago
.dockerignore
Safe
73 Bytes
Origami RL environment with Three.js viewer
3 months ago
.gitattributes
Safe
1.69 kB
chore: track binary assets with git-lfs
3 months ago
.gitignore
Safe
57 Bytes
chore: ignore pycache, outputs, and trainer state
3 months ago
Dockerfile
Safe
327 Bytes
fix: default port to 7860 for HuggingFace Spaces health check
3 months ago
HANDOFF_V2.md
Safe
16 kB
docs: add V2 handoff and plan documents
3 months ago
PLAN_V2.md
Safe
16.8 kB
docs: add V2 handoff and plan documents
3 months ago
PLAN_V3_SEQUENTIAL_TRAINING.md
Safe
34.1 kB
docs: add V3 sequential RL training architecture and implementation plan
3 months ago
README.md
Safe
1.04 kB
fix: default port to 7860 for HuggingFace Spaces health check
3 months ago
__init__.py
Safe
53 Bytes
Origami RL environment with Three.js viewer
3 months ago
client.py
Safe
1.3 kB
feat(v2): filter None fields from OrigamiAction in client step payload
3 months ago
demo.py
Safe
28.3 kB
feat: add hackathon demo script and result charts
3 months ago
modal_eval.py
Safe
6.73 kB
feat: add Modal eval script for GRPO checkpoints
3 months ago
modal_eval_v3.py
Safe
7.52 kB
fix: switch eval to A100-80GB and track completion bonus
3 months ago
modal_train.py
Safe
8.12 kB
chore(v2): add shapely dependency for PaperState intersection detection
3 months ago
modal_train_v3.py
Safe
4.01 kB
chore: switch to A100-80GB for cheaper training runs
3 months ago
models.py
Safe
226 Bytes
Rename server/ to origami_server/ to avoid module name conflict with uvicorn.server
3 months ago
pyproject.toml
Safe
671 Bytes
Rename server/ to origami_server/ to avoid module name conflict with uvicorn.server
3 months ago
requirements.txt
Safe
114 Bytes
chore(v2): add shapely dependency for PaperState intersection detection
3 months ago
uv.lock
Safe
760 kB
Origami RL environment with Three.js viewer
3 months ago