text2sql-qwen25-1p5b-lora
LoRA adapter for Qwen/Qwen2.5-1.5B-Instruct fine-tuned for text-to-SQL on b-mc2/sql-create-context.
Evaluation
Exact match on 200 held-out examples: base 0.015, fine-tuned 0.710.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct"), "krisrajz/text2sql-qwen25-1p5b-lora")
The prompt template is defined in the training repository (src/prompt.py).
- Downloads last month
- 25
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support