Spaces:

Loosebag
/

EcoGrid

Paused

App Files Files Community

EcoGrid

Commit History

Apr 26

11:15
fix: add detailed diagnostics and sync LFS tokenizer

dootisaha25

d87da64
10:52
docs: update README with troubleshooting and performance curves

dootisaha25

19e8c2c
10:46
fix: restore is_lora_valid to baseline.py

dootisaha25

4e17822
10:39
feat: restore premium UI and fix training metrics data parsing

dootisaha25

405919b
10:36
Fix plot generation to parse TRL log_history and regenerate PNGs

Loosebag

29f2560
08:37
Update trained LoRA adapter and reward curves

Loosebag

ebe0aa2
06:40
UI Overhaul, W&B Tracking, Automated Compliance Scripts, and Documentation Update for Hackathon Submission

Loosebag

743bed2
06:09
fix(space): lazy-load lora at runtime and keep dashboard responsive

Loosebag

7a41b25
06:01
chore(space): convert large lora artifacts to lfs pointers

Loosebag

91c347e
06:01
chore(space): track lora artifacts with git lfs

Loosebag

a25aa7e
05:57
fix(space): ship lora_adapter assets and enable train runtime deps

Loosebag

6d19434
05:50
fix(ui): show trained model availability and avoid misleading fallback

Loosebag

dd96d62
05:44
fix: serve streamlit dashboard on hf space

Loosebag

b98c6b9
05:35
fix: restore hf space metadata header

Loosebag

8876681
05:31
fix: stabilize deployment, action safety, and benchmark reproducibility

Loosebag

30bdd62
04:22
Fix uv sync lockfile error in Docker deployment

Loosebag

f792510
04:14
Merge pull request #2 from dooti2325/main⁠

dootisaha25

Unverified signature
d080c44
04:14
Restore critical training fixes after PR merge

Loosebag

5fac436
04:13
Resolve upstream blog conflict

dootisaha25

10cd9c8
03:58
Prepare EcoGrid hackathon submission

dootisaha25

752ff1f
03:58
Fix dead link in BLOG.md

Loosebag

baa9cb3
03:41
Update training plots with successful learning curves

Loosebag

9fbeaa6
03:32
Merge pull request #1 from dooti2325/main⁠

dootisaha25

Unverified signature
4dcd4f7
03:19
Finalize OpenEnv submission (multi-mode server, strict scoring, uv lock)

dootisaha25

578508e
02:47
Fix GRPO JSON parsing and add chat format support

Loosebag

957e370
02:38
Update README with HF space and training plots, reduce colab model size

Loosebag

d27fa17

Apr 25

19:57
Add Colab training notebook and wire real inference logic into Streamlit

Loosebag

63eb238
19:46
Refine dashboard UI with clean borders, adaptive padding, and consistent graphs

Loosebag

41555ca
19:40
Fix GridState validation crash on massive carbon overrun

Loosebag

36dae52
19:38
Add Hugging Face YAML metadata

Loosebag

47a1449
19:36
Initial commit for EcoGrid-OpenEnv hackathon

Loosebag

479b6b0
16:43
feat(colab): add RL and LLM training notebook for traffic control

Loosebag

d352264
16:16
fix(space): write utf8 metadata emoji for hf validation

Loosebag

0cec9df
16:15
merge: resolve huggingface space bootstrap README conflict

Loosebag

6d68040
16:14
feat(space): add gradio app and configure huggingface space runtime

Loosebag

035120e
16:11
initial commit

Loosebag

Unverified signature
6cd1581
16:08
feat(model): add huggingface-ready model artifacts and card metadata

Loosebag

c19dbd3
15:59
Merge branch 'main' of https://huggingface.co/Loosebag/TRLE-Hackethon

Loosebag

5c2b0ec
15:56
initial commit

Loosebag

Unverified signature
18e7a98
15:53
feat(traffic-rl): build adaptive traffic intelligence system

Loosebag

e4b7202

Commit History

Apr 26

fix: add detailed diagnostics and sync LFS tokenizer

docs: update README with troubleshooting and performance curves

fix: restore is_lora_valid to baseline.py

feat: restore premium UI and fix training metrics data parsing

Fix plot generation to parse TRL log_history and regenerate PNGs

Update trained LoRA adapter and reward curves

UI Overhaul, W&B Tracking, Automated Compliance Scripts, and Documentation Update for Hackathon Submission

fix(space): lazy-load lora at runtime and keep dashboard responsive

chore(space): convert large lora artifacts to lfs pointers

chore(space): track lora artifacts with git lfs

fix(space): ship lora_adapter assets and enable train runtime deps

fix(ui): show trained model availability and avoid misleading fallback

fix: serve streamlit dashboard on hf space

fix: restore hf space metadata header

fix: stabilize deployment, action safety, and benchmark reproducibility

Fix uv sync lockfile error in Docker deployment

Merge pull request #2 from dooti2325/main⁠

Restore critical training fixes after PR merge

Resolve upstream blog conflict

Prepare EcoGrid hackathon submission

Fix dead link in BLOG.md

Update training plots with successful learning curves

Merge pull request #1 from dooti2325/main⁠

Finalize OpenEnv submission (multi-mode server, strict scoring, uv lock)

Fix GRPO JSON parsing and add chat format support

Update README with HF space and training plots, reduce colab model size

Apr 25

Add Colab training notebook and wire real inference logic into Streamlit

Refine dashboard UI with clean borders, adaptive padding, and consistent graphs

Fix GridState validation crash on massive carbon overrun

Add Hugging Face YAML metadata

Initial commit for EcoGrid-OpenEnv hackathon

feat(colab): add RL and LLM training notebook for traffic control

fix(space): write utf8 metadata emoji for hf validation

merge: resolve huggingface space bootstrap README conflict

feat(space): add gradio app and configure huggingface space runtime

initial commit

feat(model): add huggingface-ready model artifacts and card metadata

Merge branch 'main' of https://huggingface.co/Loosebag/TRLE-Hackethon

initial commit

feat(traffic-rl): build adaptive traffic intelligence system