Spaces:

Prajwal782007
/

Gridmind

Sleeping

App Files Files Community

Gridmind

Commit History

Apr 25

08:25
feat: implement Unsloth GRPO training script with diverse reward functions and logging

adityss

d2449aa
07:53
Merge branch 'main' of https://github.com/LO-Kyu/gridmind

ShreeshantXD

c2917d2
07:50
remove binary from tracking

ShreeshantXD

5713634
07:32
feat: enable huggingface-skills plugin in cursor settings

adityss

e531486
07:30
fix: update training script with seed variation, fix reward normalization, regenerate training curves showing 0.52->0.67 improvement

adityss

bdc9954
06:00
feat: add scripts/full_demo.py — unified 10-step demo proving all 4 hackathon themes operational

adityss

5636c9d
05:34
docs: add HF blog post draft for community posting

adityss

2256ed6
05:33
fix: training reward uses 8-step rollout + /grade for genuine episode-level signal

adityss

c70e17d
05:33
feat: commit training evidence, update README with real scores, add demo scripts

adityss

8204dc0
05:16
feat: add baseline evaluation tools and demo scripts for RL performance comparison

adityss

c395f6a
05:15
chore: ignore ML outputs, models, and AI agent artifacts

adityss

e517002
05:13
fix: include env/faults.go missed due to .gitignore

adityss

61fd4d1
05:12
fix: add missing faults.go file causing HF space build error

adityss

6785dd4
05:08
feat: add GridMind GRPO training notebook using Unsloth and HF TRL

adityss

bdadba1
04:59
feat: implement Go-based GridMind-RL simulation core and update inference interface (graph)

Prajwal782007

a4671c4
04:47
docs: add reward weight rationale table to README

adityss

74dc7b5
04:23
feat: add multi-agent and planning CLI flags to inference and expose environment metadata via /info endpoint

adityss

ebe8fa5
04:11
feat: define GridMind-RL environment data models and task structures

adityss

c009bc5
04:00
feat: implement multi-component dense reward function and environmental logic for GridMind-RL

adityss

b81683f

Apr 22

12:06
Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation⁠

adityss

0af208b
05:29
Add GridMind GRPO training notebook for Colab

ShreeshantXD

fd2ceda

Apr 21

23:06
fix: Replace ineffective break with return in WebSocket close handler⁠

ShreeshantXD

d012f99
23:03
feat: Add full OpenEnv compliance⁠

ShreeshantXD

4ec4472

Apr 8

11:05
refactor: Inference and readme

ShreeshantXD

f020509
10:50
updated readme

ShreeshantXD

a4be35d
10:27
rewrite reward system

ShreeshantXD

32565e1
10:14
fix llm based reward output

ShreeshantXD

2ede269
09:19
fix: problems with parameters

ShreeshantXD

f316664
09:02
fix: reward system

ShreeshantXD

8242dc3

Apr 7

10:09
fix: introduce SCORE_EPSILON and clamp scores in run_episode and main functions

adityss

b93cee3
09:42
fix: clamp scores after rounding and ensure all sub-scores are clamped

ShreeshantXD

e58b5ec
09:03
fix: clamp all scores to open interval (0, 1) to meet validator requirements

ShreeshantXD

ef0556b
08:44
fix: mirror all base images via gcr.io

ShreeshantXD

db76306
08:39
fix: use gcr.io mirror to avoid Docker Hub rate limits

ShreeshantXD

7e27f89
08:35
fix: use golang:1.21 instead of alpine for better Docker registry compatibility

ShreeshantXD

287d2a3
08:30
fix: auto-start env server in inference.py

ShreeshantXD

30aa472
07:55
refactor: update default model and API endpoint, enhance error handling, and add close method for compatibility

adityss

891cc5b
06:56
Merge branch 'origin/main' with local changes overriding

adityss

fd3e9b6
06:53
fix: provide fallback API key and add safety check for empty observations in inference client

adityss

fe2f8c9
06:05
Sync root inference.py with fixed python/inference.py

ShreeshantXD

588b24a
05:59
Fix inference.py: handle missing API key gracefully, wrap all exceptions

ShreeshantXD

9fd03cb

Apr 6

17:24
fix: add 'server' entry point for OpenEnv validator

ShreeshantXD

427e52b
17:13
fix: add server entry point and pyproject scripts for OpenEnv validator

ShreeshantXD

91cc891

Apr 5

21:38
Merge branch 'main' of https://github.com/LO-Kyu/gridmind

adityss

0d301ce
21:30
Fix UTF-8 encoding for landing page emojis

ShreeshantXD

f75687e
21:27
Fix GitHub URL in landing page

ShreeshantXD

1838d55
21:23
Fix supervisord permissions for HF Spaces non-root user

ShreeshantXD

13a69d0
21:15
Add root landing page handler with links to dashboard and API endpoints

ShreeshantXD

90c0e10
21:08
Fix dashboard paths for /dashboard reverse proxy

ShreeshantXD

832f069
20:58
Add dashboard reverse proxy at /dashboard

ShreeshantXD

84fb786

Commit History

Apr 25

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

Merge branch 'main' of https://github.com/LO-Kyu/gridmind

remove binary from tracking

feat: enable huggingface-skills plugin in cursor settings

fix: update training script with seed variation, fix reward normalization, regenerate training curves showing 0.52->0.67 improvement

feat: add scripts/full_demo.py — unified 10-step demo proving all 4 hackathon themes operational

docs: add HF blog post draft for community posting

fix: training reward uses 8-step rollout + /grade for genuine episode-level signal

feat: commit training evidence, update README with real scores, add demo scripts

feat: add baseline evaluation tools and demo scripts for RL performance comparison

chore: ignore ML outputs, models, and AI agent artifacts

fix: include env/faults.go missed due to .gitignore

fix: add missing faults.go file causing HF space build error

feat: add GridMind GRPO training notebook using Unsloth and HF TRL

feat: implement Go-based GridMind-RL simulation core and update inference interface (graph)

docs: add reward weight rationale table to README

feat: add multi-agent and planning CLI flags to inference and expose environment metadata via /info endpoint

feat: define GridMind-RL environment data models and task structures

feat: implement multi-component dense reward function and environmental logic for GridMind-RL

Apr 22

Add Task 4 instruction following, Curriculum Manager for self-improvement, and world modeling simulation⁠

Add GridMind GRPO training notebook for Colab

Apr 21

fix: Replace ineffective break with return in WebSocket close handler⁠

feat: Add full OpenEnv compliance⁠

Apr 8

refactor: Inference and readme

updated readme

rewrite reward system

fix llm based reward output

fix: problems with parameters

fix: reward system

Apr 7

fix: introduce SCORE_EPSILON and clamp scores in run_episode and main functions

fix: clamp scores after rounding and ensure all sub-scores are clamped

fix: clamp all scores to open interval (0, 1) to meet validator requirements

fix: mirror all base images via gcr.io

fix: use gcr.io mirror to avoid Docker Hub rate limits

fix: use golang:1.21 instead of alpine for better Docker registry compatibility

fix: auto-start env server in inference.py

refactor: update default model and API endpoint, enhance error handling, and add close method for compatibility

Merge branch 'origin/main' with local changes overriding

fix: provide fallback API key and add safety check for empty observations in inference client

Sync root inference.py with fixed python/inference.py

Fix inference.py: handle missing API key gracefully, wrap all exceptions

Apr 6

fix: add 'server' entry point for OpenEnv validator

fix: add server entry point and pyproject scripts for OpenEnv validator

Apr 5

Merge branch 'main' of https://github.com/LO-Kyu/gridmind

Fix UTF-8 encoding for landing page emojis

Fix GitHub URL in landing page

Fix supervisord permissions for HF Spaces non-root user

Add root landing page handler with links to dashboard and API endpoints

Fix dashboard paths for /dashboard reverse proxy

Add dashboard reverse proxy at /dashboard