pandaind/microsoft-phi-2-fined

Model Name

Model Description

This model is a fine-tuned version of microsoft/phi-2 on Alpaca instruction dataset.

Training Details

• Base model: microsoft/phi-2
• Training dataset: Alpaca instruction dataset
• Training method: LoRA fine-tuning
• Training hardware: Google Colab GPU

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("pandaind/microsoft-phi-2-fined")
tokenizer = AutoTokenizer.from_pretrained("pandaind/microsoft-phi-2-fined")

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