Quantization made by Richard Erkhov.
This repository hosts the fine-tuned version of the GEMMA 1.1-2B model, specifically fine-tuned for a customer support chatbot use case.
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.
1from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
2
3tokenizer = AutoTokenizer.from_pretrained("your-username/your-model-name")
4model = AutoModelForCausalLM.from_pretrained("your-username/your-model-name")
5
6chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer)
7
8response = chatbot("How can I cancel my order?")
9print(response[0]['generated_text'])
