The model has been trained to better understand real-estate-related intake data and assist with extracting structured information from user inputs.
The model was fine-tuned using LoRA on top of Qwen2.5-0.5B-Instruct.
After fine-tuning, the model was quantized to 4-bit precision for reduced memory usage and efficient deployment.
This repository contains the fine-tuned model weights.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_id = "radcrew/RadEstate-Qwen2.5-0.5B-Intake"
4
5tokenizer = AutoTokenizer.from_pretrained(model_id)
6
7model = AutoModelForCausalLM.from_pretrained(
8 model_id,
9 device_map="auto"
10)
