Fine-Tuned GEMMA Model for Chatbot

This repository hosts the fine-tuned version of the GEMMA 1.1-2B model, specifically fine-tuned for a customer support chatbot use case.

Model Description

The GEMMA 1.1-2B model has been fine-tuned on the Bitext Customer Support Dataset for answering customer support queries. The fine-tuning process involved adjusting the model's weights based on question and answer pairs, which should enable it to generate more accurate and contextually relevant responses in a conversational setting.

How to Use

You can use this model directly with a pipeline for text generation:

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("your-username/your-model-name")
model = AutoModelForCausalLM.from_pretrained("your-username/your-model-name")

chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer)

response = chatbot("How can I cancel my order?")
print(response[0]['generated_text'])
Downloads last month
394
Safetensors
Model size
2.51B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train rootsec1/gemma-2B-it-customer-support