Downloads · 30 days
19
100% of all-time downloads
qwen25-3b-text2sql-lora
Akarshika/qwen25-3b-text2sql-lora
qwen25-3b-text2sql-lora is a machine learning model from Akarshika. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter that fine-tunes Qwen2.5-3B-Instruct for converting natural language questions into SQL queries, given the database schema in the prompt.
All-time downloads
19
Public
Repo size
131 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors120 MB · 91%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026
- SHA
- b033f92f
Base models
Model card
From the Hugging Face model README
Qwen2.5-3B Text-to-SQL (LoRA adapter)
LoRA adapter that fine-tunes Qwen2.5-3B-Instruct for converting natural language questions into SQL queries, given the database schema in the prompt.
Exact-match accuracy: 3/100 (base) → 75/100 (fine-tuned) on a held-out test set from b-mc2/sql-create-context. Strict exact-match scoring; manual inspection shows several functionally-equivalent misses, so this is a conservative floor.
- Method: QLoRA (r=16, alpha=16), all attention + MLP projections
- Only 0.96% of parameters trained (29.9M of 3.1B)
- Trained in ~40 min on free Kaggle T4 GPUs
Full code, eval harness, and the v1→v2 iteration story: https://github.com/TripathiAkarshika/qwen-text2sql-lora
- Library
- peft
- Created
- Sep 10, 2026
- Updated
- Sep 10, 2026