RubanAgnesh/rezolve-phi-3-mini-4k-instruct

Fine-tuned Phi-3 Model

This is a fine-tuned version of the microsoft/phi-3-mini-4k-instruct model.

Model Description

• Base model: microsoft/phi-3-mini-4k-instruct
• Fine-tuning task: Conversational AI
• Training data: Custom dataset
• Hardware used: NVIDIA H100 NVL

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("RubanAgnesh/rezolve-phi-3-mini-4k-instruct")
tokenizer = AutoTokenizer.from_pretrained("RubanAgnesh/rezolve-phi-3-mini-4k-instruct")

# Prepare your input
text = "Your prompt here"
inputs = tokenizer(text, return_tensors="pt")

# Generate
outputs = model.generate(**inputs)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Details

The model was fine-tuned with the following parameters:

• Number of epochs: 3
• Batch size: 4
• Learning rate: 2e-5
• Weight decay: 0.01

Limitations and Biases

Please note that this model inherits biases and limitations from its base model and training data.