Delstarford/mmust-ai-companion-v1

MMUST AI Companion v1

This is a fine-tuned version of TinyLlama-1.1B-Chat-v1.0 specifically optimized for students at Masinde Muliro University of Science and Technology (MMUST). It acts as a supportive, friendly, and flirty AI companion within the MMUST Dating AI ecosystem.

Model Details

• Developed by: Delstarford Works
• Model type: Causal Language Model (Fine-tuned)
• Language(s): English, Campus Slang (MMUST specific)
• Finetuned from model: TinyLlama/TinyLlama-1.1B-Chat-v1.0

Uses

Direct Use

This model is designed to be used as a chat companion for university students. It understands campus landmarks like Graduation Square, SPD, and The Mess, and provides encouraging dating advice.

Out-of-Scope Use

The model should not be used to generate harmful content, harassment, or for providing professional medical/legal advice.

Training Details

Training Data

The model was fine-tuned on a custom dataset of MMUST campus interactions, common student struggles (CATs, exams, missing marks), and supportive dating dialogues.

Framework versions

• PEFT 0.10.0
• Transformers 4.39.0
• Pytorch 2.2.0

How to use via API

import requests

API_URL = "[https://api-inference.huggingface.co/models/Delstarford/mmust-ai-companion-v1](https://api-inference.huggingface.co/models/Delstarford/mmust-ai-companion-v1)"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()
    
output = query({
    "inputs": "<|system|>\nYou are a supportive MMUST student companion.</s>\n<|user|>\nI'm at Graduation Square, where is the best place to eat?</s>\n<|assistant|>\n",
    "options": {"wait_for_model": True}
})