README: add model card highlights section and metadata snapshot.

README: add Hugging Face model link to Quick Links.

Use .git GitHub URL in HTML and Gradio links.

Gradio: update W&B line to 'example run' dashboard.

Demo copy: drop judges wording; workflow map at a glance for readers.

Expand problem narrative and Engineering Notes: time-on-SQL, Spider vs prod.

Add GitHub repo link; drop Karpathy, blog, slides, demo placeholders.

HTML demo: fix diagram crop; click-to-zoom lightbox with pan and +/- zoom.

HTML /demo: add Benchmark visuals table and three chart figures.

Gradio: fix invisible header and body text on HF dark embed.

Space home: redirect / to HTML /demo; Gradio at /gradio; fix Gradio hero.

Fix Gradio 5 mount error by moving theme/css to Blocks.

Fix Space pip resolve: fastapi>=0.115.2, python-multipart>=0.0.18, pin gradio 5.50.0.

Pin Gradio >=5.7.1 for huggingface_hub 1.x (fixes HfFolder ImportError on Space).

Point /demo and Gradio at diagram-end-to-end-workflow.png (asset on Hub via Xet).

Add workflow diagram via Hub API (Xet)

Restore optimized training diagnostics and reward curve images

Ship polished Space UI with Gradio dashboard and evidence-rich demo.

Upload artifacts/runs/20260426-064318-sample-rewards-32eval/sample_rewards_final.json with huggingface_hub

Upload folder using huggingface_hub

Add training artifacts 20260426-050707

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Add training artifacts 20260426-032246

Add training artifacts 20260425-202751

Avoid whoami rate-limit during job submission

Harden HF job token wiring and persist full training outputs

Fix TRL 0.18 compatibility: remove unsupported generation_kwargs; set safety flags on model.generation_config.

Harden GRPO generation stability on CUDA: bf16 + eager attention + invalid-logit guards.

Fix GRPO batch/generation mismatch: auto-adjust num_generations; set launcher default to 2.

Simplify HF training stack: remove unsloth/vllm path, use plain transformers AutoModel + single OpenEnv reward.

Fix Unsloth startup: avoid pre-importing trl/transformers; mock vllm as real package modules.

Fix HF job startup: import unsloth first and shim vllm package metadata check.

Fix HF Job bootstrap: transformers>=4.51 for trl 0.18, datasets<4; simplify to colab-style OpenEnv SQL reward.

Fix HF Jobs bootstrap (pin transformers/trl, drop torchao stack); add reward and trainer JSONL logging; stabilize launch_job.

changes in ultimate sota

Fix: Mock vllm and llm_blender to stabilize GRPOTrainer in HF Jobs environment

Downgrade TRL to 0.22.2 to natively bypass experimental vllm dependencies

Fix vllm error cleanly by creating fake python module structure

Add vllm to dependencies to fix TRL's hard import requirement

Remove vllm mock to fix importlib find_spec crash in TRL 0.23

Mock vllm to bypass TRL missing module error

Downgrade TRL to <0.24.0 to fix missing dependency chain

Add TRANSFORMERS_CACHE mock to fix TRL/llm_blender crash

Fix llm-blender ModuleNotFoundError

Ensure TRL GRPO imports by installing mergekit

Prevent torchvision import crashes in HF Jobs

Make OpenEnv training+API judge-proof

Add --break-system-packages for Ubuntu 24.04 (PEP-668)

Fix TRL and Torchao dependency conflicts