remove NARADA_CLAUDE_CODE_PROMPT.md

remove Guidlines.txt

update README.md

add Blog.md

add kl_divergence.png

add reward_std.png

add reward_curve.png

add loss_curve.png

add before_after.png

Multi-step GRPO, milestone reward, benchmark, Neo4j export, graph viz

Increase GRPO diversity: G=8, temperature=1.1

Add CLAUDE.md with recurring training bug patterns

Fix narada_grpo.ipynb Cell 6: handle TRL chat-format completions

Fix narada_grpo.ipynb Cell 3: disable Unsloth stats + thinking mode

Fix narada_grpo.ipynb: max_completion_length 300 -> 600

upgrades for openenv validation

Fix notebook cell source encoding (char-split artifact from editor)

Add real multi-model benchmark results to README

Add phenotypes_absent obs field, fix training config, update README framing

rules added for training and evaluation of Narada-CLAUDE, along with a colab notebook for training. Also added a prompt for generating code using Narada-CLAUDE.

Add contributing guide, local setup instructions, and .env.example

Add training notebook, architecture docs, baseline benchmark, and WS fixes

Add OpenEnv standard endpoints and uv.lock

Add HF Space frontmatter to README

Rename project to Narada

Initial ClinDetect OpenEnv environment