Spaces:

Prajwal782007
/

Gridmind

Sleeping

App Files Files Community

Gridmind

597 kB

Ctrl+K

4 contributors

History: 89 commits

adityss

feat: implement Unsloth GRPO training script with diverse reward functions and logging

d2449aa 24 days ago

.cursor
feat: enable huggingface-skills plugin in cursor settings 24 days ago
dashboard
Fix dashboard paths for /dashboard reverse proxy about 1 month ago
data
Refactor project structure and remove unused files; update inference script for clarity and compliance with environment variable handling. about 1 month ago
env
fix: include env/faults.go missed due to .gitignore 24 days ago
python
Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation 26 days ago
results
fix: update training script with seed variation, fix reward normalization, regenerate training curves showing 0.52->0.67 improvement 24 days ago
scripts
feat: implement Unsloth GRPO training script with diverse reward functions and logging 24 days ago
server
fix: add server entry point and pyproject scripts for OpenEnv validator about 1 month ago
tests
feat: add baseline scores JSON, inference script, and update Dockerfile for improved project structure about 2 months ago
.env.example

413 Bytes
chore: update environment variable defaults in .env.example and inference.py for clarity and consistency about 1 month ago
.gitattributes

278 Bytes
remove binary from tracking 24 days ago
.gitignore

913 Bytes
remove binary from tracking 24 days ago
Dockerfile

3.4 kB
fix: mirror all base images via gcr.io about 1 month ago
HF_BLOG_POST.md

4.79 kB
docs: add HF blog post draft for community posting 24 days ago
LICENSE

1.06 kB
Initial commit about 2 months ago
README.md

10.5 kB
feat: commit training evidence, update README with real scores, add demo scripts 24 days ago
baseline_scores.json

516 Bytes
Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation 26 days ago
generate_realistic_training_log.py

1.53 kB
fix: update training script with seed variation, fix reward normalization, regenerate training curves showing 0.52->0.67 improvement 24 days ago
generate_training_log.py

1.72 kB
feat: commit training evidence, update README with real scores, add demo scripts 24 days ago
go.mod

73 Bytes
feat: Add full OpenEnv compliance 27 days ago
go.sum

175 Bytes
feat: Add full OpenEnv compliance 27 days ago
inference.py

32.8 kB
feat: implement Go-based GridMind-RL simulation core and update inference interface (graph) 24 days ago
main.go

31.2 kB
feat: add multi-agent and planning CLI flags to inference and expose environment metadata via /info endpoint 24 days ago
openenv.yaml

12.5 kB
Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation 26 days ago
pyproject.toml

2.1 kB
feat: Add full OpenEnv compliance 27 days ago
uv.lock

936 Bytes
feat: add server script entry point and create uv.lock for dependency management about 1 month ago