You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Duration LoRA Chatbot

A LoRA-fine-tuned adapter for DialoGPT-medium, specialized in person activity tracking queries (e.g., "How long was Dhashini on-screen?").

Usage

Load as a PEFT adapter for causal LM tasks. Example prompt:
Context: You are an AI assistant for person activity tracking. Current data: Dhashini: on-screen 00:05:30. Question: How long was Dhashini on-screen?

How to Run

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "microsoft/DialoGPT-medium"
model = AutoModelForCausalLM.from_pretrained(base)
model = PeftModel.from_pretrained(model, "Dhashini/duration-lora-chatbot")
tokenizer = AutoTokenizer.from_pretrained(base)

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Downloads last month: 8

Model tree for Dhashini/duration-lora-chatbot

Base model

microsoft/DialoGPT-medium

Adapter

(31)

this model