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:
Veer15
/
faultline-env-train
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
faultline-env-train
2.18 MB
Ctrl+K
Ctrl+K
3 contributors
History:
101 commits
Veer15
Upload README.md
15c5622
verified
about 1 month ago
dashboard
remove the redundant section in the dashboard
about 1 month ago
docs
docs: add training.md operator quickstart, remove superpowers planning artifacts
about 1 month ago
evals
add provider interface
about 1 month ago
internal
docs: update project plan to define multi-agent red/blue wargames, training curriculum, and environment integration details
about 1 month ago
mesh
feat: port WarGames phase 0 environment
about 1 month ago
outputs
Add qwen3-8b red vs blue showdown output
about 1 month ago
scripts
publish: inline chat template into tokenizer_config for HF chat compatibility
about 1 month ago
server
feat: port WarGames phase 0 environment
about 1 month ago
src
Update Red/Blue showdown behavior and refresh Qwen benchmark artifacts.
about 1 month ago
tests
env_client: retry transient 5xx + typed EnvUnavailableError; trainer survives env outages
about 1 month ago
training
docs: correct HF endpoint deployment command
about 1 month ago
.dockerignore
67 Bytes
feat: port WarGames phase 0 environment
about 1 month ago
.gitignore
187 Bytes
tsconfig fix
about 1 month ago
Dockerfile
2.04 kB
feat: add spaces hosting docker workflow
about 1 month ago
Dockerfile.inference
2.08 kB
feat: add spaces hosting docker workflow
about 1 month ago
Makefile
713 Bytes
feat: add spaces hosting docker workflow
about 1 month ago
README.md
6.47 kB
Upload README.md
about 1 month ago
blog.md
15.5 kB
Update blog.md
about 1 month ago
inference.py
14.8 kB
Update Red/Blue showdown behavior and refresh Qwen benchmark artifacts.
about 1 month ago
openenv.yaml
1.86 kB
feat: add blue defender curriculum
about 1 month ago
pyproject.toml
1.08 kB
Bump vllm>=0.11 (TRL 0.25 needs StructuredOutputsParams; only present in vllm 0.11+)
about 1 month ago
pyrightconfig.json
75 Bytes
refactor: enhance type safety in inference and evaluation scripts; update pyright config to exclude specific directories
about 1 month ago
start.sh
1.97 kB
feat: add spaces hosting docker workflow
about 1 month ago
uv.lock
1.35 MB
rollout: mask think block from GRPO loss + free GPU before merge subprocess
about 1 month ago