hybridaione/LFM2.5-1.2B-Text2SQL-MLX

LFM2.5-1.2B-Text2SQL (MLX)

A fine-tuned version of LiquidAI/LFM2.5-1.2B-Instruct for Text-to-SQL generation.

Model Description

This model was fine-tuned on 2000 synthetic Text-to-SQL examples generated using a teacher model (DeepSeek V3). The fine-tuning was performed using LoRA adapters with MLX on Apple Silicon, then fused into the base model.

Training Details

• Base Model: LiquidAI/LFM2.5-1.2B-Instruct
• Training Data: 2000 synthetic examples
• Training Method: LoRA fine-tuning (FP16)
• Iterations: 5400
• Hardware: Apple Silicon (MLX)

Performance

Model Comparison

Metric	Teacher (DeepSeek V3)	Base Model	Fine-tuned
Exact Match	60%	48%	72%
LLM-as-Judge	90%	75%	87%
ROUGE-L	92%	83%	94%
BLEU	85%	70%	89%
Semantic Similarity	96%	93%	97%

Training Progression

The model shows consistent improvement across all checkpoints with no signs of overfitting.

Usage

MLX (Apple Silicon)

from mlx_lm import load, generate

model, tokenizer = load("hybridaione/LFM2.5-1.2B-Text2SQL-MLX")

# Example query
prompt = '''CREATE TABLE employees (id INT, name VARCHAR, salary DECIMAL);

Question: What are the names of employees earning more than 50000?'''

response = generate(model, tokenizer, prompt=prompt, max_tokens=256)
print(response)

License

This model is released under the Apache 2.0 license, following the base model's license.