Official implementation of 'LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention'.

LLaMA-Adapter (from Midjourney)

This repo proposes LLaMA-Adapter, a lightweight adaption method for fine-tuning instruction-following LLaMA models 🔥, using 52K data provided by Stanford Alpaca.

Try out the web demo 🤗 of LLaMA-Adapter:

Efficiency Comparison:

By inserting adapters into LLaMA's transformer, our method only introduces 1.2M learnable parameters, and turns a LLaMA into an instruction-following model within 1 hour. For stablizing training at early stages, we propose a novel Zero-init Attention with zero gating mechanism to adaptively incorporate the instructional signals. After fine-tuning, LLaMA-Adapter can generate high-quality instruction-following sentences, comparable to the fully fine-tuned Stanford Alpaca and Alpaca-Lora.

Our approach can be simply extended to Multi-modal Input Instructions. The reasoning framework of image-conditioned LLaMA-Adapter for ScienceQA is as follows, which is also shared by other modalities, such as audio and video.

• TODO: Multi-modal LLaMA-Adapter, Adapters for larger-scale LLaMA models
• The Training Code for LLaMA-7B is available in alpaca finetune v1 📌.
• Paper is available on arXiv.
• The generation code of LLaMA-Adapter based on 7B LLaMA has been released.
• 🔥 We are hiring interns, postdocs and full-time researchers in General Vision Group, Shanghai AI Lab, aiming at multi-modality and vision foundation models. If you are interested, please contact [email protected].

Here is a from-scratch script.

conda create -n llama_adapter -y python=3.8
conda activate llama_adapter

# install pytorch
conda install pytorch cudatoolkit -c pytorch -y

# install dependency and llama-adapter
pip install -r requirements.txt
pip install -e .

Please request access to the pre-trained LLaMA from this form (official) or download the LLaMA-7B from Hugging Face (unofficial). Then, obtain the weights of our LLaMA-Adapter from here. We denote the path to the downloaded weights of LLaMA and adapters as TARGET_FOLDER and ADAPTER_PATH.

Here is an example to generate instruction-following sentences with 7B LLaMA model and our LLaMA-Adapter:

torchrun --nproc_per_node 1 example.py \
         --ckpt_dir $TARGET_FOLDER/model_size\
         --tokenizer_path $TARGET_FOLDER/tokenizer.model \
         --adapter_path $ADAPTER_PATH

We release the simple fine-tuning code of LLaMA-Adapter on LLaMA-7B model at here, which is for effortless reproduction with minimal dependencies. We will soon release the fine-tuning code for LLaMA-65B and multi-model LLaMA-Adapter.

Please download the 52K instruction-following training data from Standford Alpaca, and put it under DATA_PATH. Then run:

cd alpaca_finetuning_v1

torchrun --nproc_per_node 8 finetuning.py \
         --model Llama7B_adapter \
         --llama_model_path $TARGET_FOLDER/ \
         --data_path $DATA_PATH/alpaca_data.json \
         --adapter_layer 30 \
         --adapter_len 10 \
         --max_seq_len 512 \
         --batch_size 4 \
         --epochs 5 \
         --warmup_epochs 2 \
         --blr 9e-3 \
         --weight_decay 0.02 \
         --output_dir ./checkpoint/

Tell me about alpacas.

• LLaMA-Adapter: Alpacas are members of the camelid family and are native to the Andes Mountains of South America. They are typically found in herds of 10-20 animals and are known for their gentle nature and their ability to thrive in harsh climates. Alpacas are typically white or grey in color and have long, silky coats. They are also known for their ability to produce high-quality wool, which is used in the production of clothing and other products.

Tell me about the president of Mexico in 2019.

• LLaMA-Adapter: The president of Mexico in 2019 was Andrés Manuel López Obrador, who took office on December 1st, 2018. He is a member of the left-wing party Morena and is known for his populist policies. He has focused on tackling corruption, reducing poverty, and improving the country's infrastructure. He has also been a vocal critic of the United States' immigration policies.

Write a Python program that prints the first 10 Fibonacci numbers.

• LLaMA-Adapter:

def fibonacci():
    a = 0
    b = 1
    for i in range(10):
        a, b = b, a + b
        print(a, b)
    print("Fibonacci numbers: ", a, b)

fibonacci()

def fibonacci(n):
    if n == 0:
        return 0
    elif n == 1:
        return 1
    else:
        return fibonacci(n-1) + fibonacci(n-2)

print(fibonacci(10))

numbers = [0, 1]

for i in range(2, 11):
    numbers.append(numbers[i-2] + numbers[i-1])

print(numbers)
# Output: [0, 1, 1, 2, 3, 5, 8, 13, 21, 34]

# Fibonacci numbers are the numbers in the following integer sequence, called the Fibonacci sequence, and characterized by the fact that every number after the first two is the sum of the two preceding ones.

# Fibonacci sequence: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...

# Program:

# Initialize the first two numbers of the Fibonacci sequence
a = 0
b = 1

# Print the first 10 numbers of the Fibonacci sequence
print(a)
print(b)

for i in range(2,10):
    c = a + b
    a = b
    b = c
    print(c)

Write a program that prints the numbers from 1 to 100. But for multiples of three print 'Fizz' instead of the number and for the multiples of five print 'Buzz'. For numbers which are multiples of both three and five print 'FizzBuzz'.

• LLaMA-Adapter:

def print_numbers(n):
    for i in range(1, 101):
        if i % 3 == 0 and i % 5 == 0:
            print("FizzBuzz")
        elif i % 3 == 0:
            print("Fizz")
        elif i % 5 == 0:
            print("Buzz")
        else:
            print(i)

for i in range(1, 101):
    if i % 3 == 0 and i % 5 == 0:
        print("FizzBuzz")
    elif i % 3 == 0:
        print("Fizz")
    elif i % 5 == 0:
        print("Buzz")
    else:
        print(i)

for i in range(1, 101):
    if i % 3 == 0 and i % 5 == 0:
        print('FizzBuzz')
    elif i % 3 == 0:
        print('Fizz')
    elif i % 5 == 0:
        print('Buzz')
    else:
        print(i)

for (let i = 1; i <= 100; i++) {
  if (i % 3 === 0 && i % 5 === 0) {
    console.log("FizzBuzz");
  } else if (i % 3 === 0) {
    console.log("Fizz");
  } else if (i % 5 === 0) {
    console.log("Buzz");
  } else {
    console.log(i);
  }
}

Peng Gao, Jiaming Han, Renrui Zhang, Aojun Zhou

If you find our LLaMA-Adapter code and paper useful, please kindly cite:

@article{llamaadapter2023,
  title = {LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention},
  author={Zhang, Renrui and Han, Jiaming and Zhou, Aojun and Hu, Xiangfei and Yan, Shilin and Lu, Pan and Li, Hongsheng and Gao, Peng and Qiao Yu},
  journal={arXiv preprint arXiv:2303.16199},
  year={2023}
}

This repo benefits from LLaMA, Stanford Alpaca, and Alpaca-Lora. Thanks for their wonderful works.