Upload 2 files

Update README.md

Update README.md

Upload 7 files

Upload BLOG.md

Update requirements.txt

Delete grpo_train.py

Upload grpo_training.ipynb

Upload README.md with huggingface_hub

Upload BLOG.md with huggingface_hub

Upload requirements.txt with huggingface_hub

Update requirements.txt

Update requirements.txt

Update requirements.txt

Added ai_pm_prompts.json for env training

Added training of RL environment script with unsloth and HF GPU cloud

Added validate.sh for secure and working environment

Added fastapi server for deployment space

Fixed readme as per deployment requirement

Added basic configs for env needed with dockerfile for deployment on space

feat: add eval baseline script (inference testing for env), report, prompter, and env config

Initialized RL environment

Created RL schemas and prompter for RL environment

Made code structure based on prev env style

Update README.md

Initial commit