metadata

language:
  - en
license: other
datasets:
  - vicgalle/alpaca-gpt4

phi-1_5-qlora-alpaca-instruction Model Card

Model Description

This model is a causal language model based on the microsoft/phi-1_5 and has been finetuned using QLORA technology on the vicgalle/alpaca-gpt4 dataset.

Fine-tuning Details

Base Model: microsoft/phi-1_5
Fine-tuning Dataset: vicgalle/alpaca-gpt4
Hardware: NVIDIA 3090ti
Training Duration: 14 hours
VRAM Consumption: Approx. 20 GB
Token Max Length: 2048
Model Size: 1.5billion + qlora weights merged

Hyperparameters

# Lora Configuration
config = LoraConfig(
    r=16,
    lora_alpha=16,
    target_modules=["Wqkv", "out_proj"],
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM"
)

# Training Hyperparameters
training_arguments = TrainingArguments(
        output_dir=f"{local_path}/output_dir",
        per_device_train_batch_size=4,
        gradient_accumulation_steps=6,
        learning_rate=2e-4,
        lr_scheduler_type="cosine",
        evaluation_strategy = "steps",
        eval_steps=500,
        save_strategy="epoch",
        logging_steps=100,
        num_train_epochs=6,
        report_to = 'wandb',
        run_name = run_name
    )

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nps798/phi-1_5-qlora-alpaca-instruction"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map={"": 0},
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    model_name,
    trust_remote_code=True
)

prompt= """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Choose three places you would like to visit and explain why.

### Response:"""
inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=500)
text = tokenizer.batch_decode(outputs)[0]
print(text)

Example

Question	Original phi 1.5	This fine-tuned model
I'm planning to visit Taiwan soon. Can you recommend some local festivals or cultural events that I shouldn't miss?	There are many festivals and cultural events in Taiwan that you should definitely check out. Some popular ones include the Dragon Boat Festival, the Mid-Autumn Festival, and the Dragon Boat Festival Parade. You can also visit the Taiwan Museum of Natural History to learn more about the country's rich history and culture.	1. Taipei City: This is the capital of Taiwan and is known for its modern architecture, shopping, and nightlife.2. Taipei Zoo: This is one of the largest zoos in the world, and it's home to a wide variety of animals, including tigers, elephants, and gorillas.3. Taipei Gardens: This is a large botanical garden that features a wide variety of plants, including tropical flowers, shrubs, and trees.4. Taipei Park: This is a large park that features a variety of attractions, including a zoo, a botanical garden, and a zoo.5. Taipei Aquarium: This is one of the largest aquariums in the world, and it features a wide variety of marine animals, including dolphins, whales, and sharks.6. Taipei International Airport: This is the largest airport in the world, and it's home to a wide variety of airlines, including American, British, and Japanese.7. Taipei International Museum: This is one of the largest museums in the world, and it features a wide variety of exhibits, including art, history, and science.8. Taipei International School: This is one of the largest schools in the world, and it's home to a wide variety of students, including children, teenagers, and adults.
Row2Col1	Row2Col2	Row2Col3
Row3Col1	Row3Col2	Row3Col3

License

Because the base model is microsoft phi-1.5b model, this fine-tuned model is provided under the MICROSOFT RESEARCH LICENSE and is meant for non-commercial use only.

Author

I am a medical doctor interested in ML/NLP field. If you have any advice, suggestions, or opportunities, or simply want to discuss the fascinating intersection of medicine and technology, please don't hesitate to reach out.