Update README.md

Update README.md

readme updated

Update README.md

Update README for clarity on baseline scores

Update clone URL in README for local setup

README updated

Demo Site ready

feat(notebooks): add Kaggle 1xT4 GRPO notebook and refresh 2xT4 sibling

feat(training): add A6000 single-GPU GRPO trainer with dense reward + curriculum

feat(kaggle nb): integrate Liger-Kernel for fused Triton kernels on 2xT4

feat(notebooks): add Kaggle 2x T4 GRPO training notebook

chore(noise): silence ToolError WARNING spam and Qwen max_length warnings

env added

chore: replace fake hf_ placeholder in .env.example to avoid HF secret-scanner warning

done

notebook

assets added

phase-1

Initial commit