Fetching metadata from the HF Docker repository...
Delete generate_plots.py
1d191e4 verified - docs Polish for hackathon submission: training evidence, two pipelines, UI, docs
- scripts feat: curriculum training + Karnataka scenarios + repo cleanup
- server OpenGrid: Multi-agent POMDP power grid environment with GRPO training
- src feat: curriculum training + Karnataka scenarios + repo cleanup
- static Polish for hackathon submission: training evidence, two pipelines, UI, docs
- tests OpenGrid: Multi-agent POMDP power grid environment with GRPO training
- training Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 701 Bytes Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 211 Bytes OpenGrid: Multi-agent POMDP power grid environment with GRPO training
- 731 Bytes Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 1.61 kB Drop unsloth: use standard bitsandbytes 4-bit + peft LoRA + TRL GRPOTrainer
- 1.07 kB OpenGrid: Multi-agent POMDP power grid environment with GRPO training
- 22.1 kB docs(readme): point blog links to the HF Space copy of blog.md
- 3.25 kB GRPO training with CUDA + results in UI
- 15.7 kB Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 28.6 kB docs: clarify scenario count, OPENGRID_MODE flag; drop runtime/epoch info
- 1.6 kB Fix health check timeout: start UI server in background before training
- 19.6 kB feat: curriculum training + Karnataka scenarios + repo cleanup
- 1.37 kB feat: curriculum training + Karnataka scenarios + repo cleanup
- 1.27 kB Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 834 Bytes OpenGrid: Multi-agent POMDP power grid environment with GRPO training
- 916 Bytes Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 275 Bytes Drop unsloth: use standard bitsandbytes 4-bit + peft LoRA + TRL GRPOTrainer
- 98 Bytes OpenGrid: Multi-agent POMDP power grid environment with GRPO training
- 20.2 kB Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 19.5 kB Polish for hackathon submission: training evidence, two pipelines, UI, docs
- 2.88 kB OpenGrid: Multi-agent POMDP power grid environment with GRPO training