Replace mermaid block in README.md with ASCII diagram (renders in HF blob viewer)

Replace mermaid block in BLOG.md with ASCII diagram (renders in HF blob viewer)

Update models.py: humanise voice, narrative, captions

Update model_cards/sft_adapter_README.md: humanise voice, narrative, captions

Update gradio_app.py: humanise voice, narrative, captions

Update docs/architecture.md: humanise voice, narrative, captions

Update devops_pipeline_gym_colab.ipynb: humanise voice, narrative, captions

Update README.md: humanise voice, narrative, captions

Update BLOG.md: humanise voice, narrative, captions

BLOG: add header rows to TL;DR + SFT-setup tables (was rendering empty bars)

frontier_results: add 5 frontier baseline JSONs (evidence behind comparison numbers)

Notebook: strip PREVIOUS HANDOFF NOTES line; remove broken Kaggle badge

grpo_train: strip PREVIOUS HANDOFF NOTES from prompt template

video_script: fill placeholders, fix framing line

README: inline architecture mermaid; +200 steps in GRPO; drop broken Kaggle badge

gradio_app docstring: stale +3.225 -> +1.156

BLOG: rebuild as full artifact (mermaid arch, tables, results, GRPO chart, code, artifacts list)

Honest reframe: baseline is Qwen2.5-7B (not Qwen3-1.7B); trained 1.7B beats every untrained baseline tested

Honest reframe: baseline is Qwen2.5-7B (not Qwen3-1.7B); trained 1.7B beats every untrained baseline tested

Replace 30-step GRPO curve with 200-step retry curve

README: footnote on single-seed vs n=3 methodology

Colab: drop Track-IO link, add concrete +1.156 number in wrap-up

Colab notebook with executed output cells visible to judges

Lock in real numbers: +1.156 same-model delta, beats all 70B+ frontier (BLOG.md)

Lock in real numbers: +1.156 same-model delta, beats all 70B+ frontier (README.md)

README: add Gradio Demo Space badge

Drop dead Track-IO link, add Kaggle badge

Colab: align baseline+trained temp to 0.3 (apples-to-apples)

Colab: add Kaggle badge, honest GRPO cell, cleaner wrap-up

Hackathon submission: new README (3-5 min read), BLOG.md narrative, frontier baselines, design-principles framing

README: add Colab/Kaggle badges + judge re-run instructions + adapter links

Submission deliverables: Colab notebook + per-step CSV + trainer log upload

Phase M Stage B: align fully with kube-sre-gym (sid-rp) patterns + A100 prep

Phase M Option 3 v3: 3 fixes lifted from kube-sre-gym (sid-rp) GRPO patterns

Phase M Option 3 retry: vLLM debug logging + reduce gpu_memory + max-steps 30

Phase M Option 3 hotfix: re-add vllm to PEP 723 deps

Phase M Option 3: vLLM single LoRA, no SFT adapter

Phase M: handle string config_edits + remove debug logger

Phase M debug: log raw parse_completion data to see config_edits shape

Phase M Stage B: Option A coerce dict->list + bump to 200 steps

Phase M smoke test wrapper: 20 steps for fast validation

Phase M Stage A v2: fix 3 compound bugs preventing GRPO learning

Phase M Stage A: revert wrapper + trainer to 4940a15 (last known-working non-vLLM state)

Phase M Stage A: revert --use-vllm, ship non-vLLM path

Phase M debug Approach 2.5: pin peft>=0.18.0,<0.19 for SFT adapter loading

Phase M debug Approach 2: revert vllm pin + enforce_eager=True

Phase M Stage A vLLM Approach 1: pin vllm==0.6.3 (avoid v1-engine graph bug)

Phase M Stage A vLLM: enable use_vllm + fast_inference for ~3x speedup

Phase M Stage A: --max-steps 100, fix Track-IO wiring

Phase M-prep fix: append /final to sft_path in GRPO wrapper