metadata
library_name: peft
base_model: Qwen/Qwen2.5-Coder-1.5B
pipeline_tag: text-generation
tags:
- text-to-sql
- sql
- lora
- qwen2.5-coder
- fine-tuned
Text2SQL-LoRA
A parameter-efficient fine-tuned language model for natural-language-to-SQL generation.
Base Model
Qwen/Qwen2.5-Coder-1.5B
Fine-tuning
- Method: LoRA
- Rank: 16
- Alpha: 32
- Dropout: 0.05
- Task: Causal Language Modeling
Intended Use
Research and experimentation in Text-to-SQL generation.
Limitations
Generated SQL should be validated before execution.