NovaBrew Customer Support Bot
Fine-tuned version of Qwen2.5-1.5B-Instruct for NovaBrew customer support using QLoRA.
Model Details
- Base model: Qwen/Qwen2.5-1.5B-Instruct
- Fine-tuning method: QLoRA (4-bit quantization + LoRA)
- LoRA rank: 16
- Training examples: 10 NovaBrew support Q&A pairs
- Task: Customer support for NovaBrew smart coffee machines
Training
Trained using PEFT + TRL on a custom NovaBrew dataset. Part of the llm-finetune-journey project.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base_model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2.5-1.5B-Instruct",
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(model, "anaishadh/novabrew-support-bot")
tokenizer = AutoTokenizer.from_pretrained("anaishadh/novabrew-support-bot")
Example
User: How do I reset my NovaBrew?
Bot: To factory reset your NovaBrew, hold the power button and the brew button simultaneously for 10 seconds until the LED flashes red three times.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support