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.
- Downloads last month
- 29
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B") model = PeftModel.from_pretrained(base_model, "sachiin051/Text2SQL-LoRA")