Modelpublic

ynanxiu/qwen25-1.5b-coffee-lora

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes7downloads

Model Card

Qwen2.5-1.5B Coffee LoRA

LoRA adapter fine-tuned on the coffee-barista-dataset for coffee domain expertise and tool calling.

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "Qwen/Qwen2.5-1.5B-Instruct"
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, "ynanxiu/qwen25-1.5b-coffee-lora")
tokenizer = AutoTokenizer.from_pretrained(base)

Latest version: v2

—94/100 chat quality
—19/20 tool calling
—Q4KM GGUF: 940 MB