Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+license: apache-2.0
+tags:
+  - text-to-sql
+  - grpo
+  - lora
+  - zeroproof
+datasets:
+  - zero-proof-ai/text-to-sql-shop
+---
+
+# text-to-sql-shop-r2
+
+LoRA adapter on `Qwen/Qwen3-4B` from training run `run_b250062f96c07786` of the
+[`recipes/04-train/text-to-sql`](https://github.com/Zero-Proof-AI/zeroproof-sdk/tree/main/recipes/04-train/text-to-sql)
+recipe (execution-match reward on a seeded Postgres schema). Holdout pass@1 at this
+checkpoint: 0.604 (140 tasks, 4 samples each, thinking on).
+Its holdout rollouts are the `eval-r2` config of `zero-proof-ai/text-to-sql-shop`.
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B")
+model = PeftModel.from_pretrained(base, "zero-proof-ai/text-to-sql-shop-r2")
+```