Downloads · 30 days
0
text2sql-llama1b-cot-lr5e-5-l16
yashcse21/text2sql-llama1b-cot-lr5e-5-l16
text2sql-llama1b-cot-lr5e-5-l16 is a machine learning model from yashcse21. 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 mlx. The card lists the license as llama3.2.
MLX LoRA adapter fine-tuned from mlx-community/Llama-3.2-1B-Instruct-bf16 to turn a natural-language question + a CREATE TABLE schema into a schema-faithful SQLite SELECT (reasoning models emit Reasoning: … / SQL: …).
Access
Public
Updated Jun 18, 2026
Repo size
67.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors90.3 MB · 100%
At a glance
- Library
- mlx
- License
- llama3.2
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026
- SHA
- 675dac42
Base models
Model card
From the Hugging Face model README
Text-to-SQL · cot_lr5e-5_L16
MLX LoRA adapter fine-tuned from
mlx-community/Llama-3.2-1B-Instruct-bf16 to turn a natural-language question + a CREATE TABLE schema into a
schema-faithful SQLite SELECT (reasoning models emit Reasoning: … / SQL: …).
# download the adapter, then:
from mlx_lm import load
model, tok = load("mlx-community/Llama-3.2-1B-Instruct-bf16", adapter_path="<downloaded-adapter-dir>")
Pair generation with a deterministic AST guardrail (single read-only SELECT). See the project repo for the data pipeline, study, and evaluation.
- Library
- mlx
- License
- llama3.2
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026