Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
cazyundee
/
training
Like
0
Paused
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
training
465 kB
Ctrl+K
Ctrl+K
1 contributor
History:
49 commits
cazyundee
CPU-only: drop `spaces`/ZeroGPU (403 PRO required wedged the Space in RUNTIME_ERROR)
c7587c6
verified
9 days ago
docs
log: retract v7-v12 KL conclusion; metric artifact + logp_floor fix
9 days ago
experiments
fix: repetition feature lost in FEN round-trip (train/inference mismatch); greedy-health exp
10 days ago
scripts
add learn-phase thread benchmark
10 days ago
tests
parallel self-play (--workers), conversion experiments, whitelist
10 days ago
tinychess
fix 2nd train/inference mismatch: last-move feature lost in FEN round-trip
10 days ago
.gitattributes
Safe
1.52 kB
initial commit
12 days ago
README.md
Safe
2 kB
fix: gradio 5 for huggingface_hub>=1.0 compat
12 days ago
app.py
Safe
18.8 kB
CPU-only: drop `spaces`/ZeroGPU (403 PRO required wedged the Space in RUNTIME_ERROR)
9 days ago
inspect_trace.py
Safe
6.24 kB
tinychess: self-play research substrate (phase 1-4)
12 days ago
requirements.txt
Safe
66 Bytes
CPU-only: drop `spaces`/ZeroGPU (403 PRO required wedged the Space in RUNTIME_ERROR)
9 days ago
train_selfplay.py
Safe
27.4 kB
--logp-floor: exclude Dirichlet-forced samples (logp_old<-50, 0.9%) from PPO ratio; worst-sample kl 22015->35, max grad 254->45
10 days ago