Instructions to use HideIron/tiny-aya-global-sql-selfheal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HideIron/tiny-aya-global-sql-selfheal with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global") model = PeftModel.from_pretrained(base_model, "HideIron/tiny-aya-global-sql-selfheal") - Notebooks
- Google Colab
- Kaggle
tiny-aya-global-sql-selfheal (DPO)
LoRA adapter for CohereLabs/tiny-aya-global (3.35B) from a fully automated self-healing text-to-SQL loop (Lexsi Labs Hackathon, Track 3, PS #8). Failures are detected by executing the SQL on real Spider databases, classified, corrected by Aya Expanse 32B (every fix verified by execution; the healer never sees the gold query), and retrained through AgentTune. Deployment is decided by AgentTune's DeploymentGate on held-out data.
Recipe: DPO (AgentTune RetrainConfig, TRL), LoRA r=16/alpha=32 on all projections, 158 verified pairs, 3 epochs, lr 1e-5, beta 0.1.
Result: Gate split 58.0% vs baseline 62.0% (-4pp, fixed 4 / broke 8); test 44.6% vs 45.6%. The DeploymentGate BLOCKED this adapter (task accuracy regressed). The write-up explains why: likelihood displacement on minimal-edit SQL pairs plus catastrophic forgetting.
- Project page + code: https://huggingface.co/spaces/HideIron/selfheal-sql
- All run logs and gate decisions: https://huggingface.co/datasets/HideIron/selfheal-sql-runs
- Training data: 158 execution-verified fix pairs (heal/baseline-pool600 in the runs repo)
- Downloads last month
- 21