mtu-chatbot-qwen

MTU Chatbot - Qwen Fine-tuned

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct specifically trained on Mother Teresa University (MTU) data.

Model Details

• Base Model: Qwen/Qwen2.5-1.5B-Instruct
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Training Data: MTU institutional documents and information
• Use Case: University chatbot for student and staff inquiries

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Indrifazliji/mtu-chatbot-qwen")
model = AutoModelForCausalLM.from_pretrained("Indrifazliji/mtu-chatbot-qwen")

# Generate response
input_text = "Tell me about MTU programs"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Configuration

• LoRA Rank: 16
• LoRA Alpha: 32
• Learning Rate: 0.0002
• Epochs: 1
• Batch Size: 4

Limitations

This model is specifically trained for MTU-related queries and may not perform well on general topics outside the university domain.