Mobillama 1B Chat

🚀 MobiLlama-1B-Chat

MobiLlama-1.2B-Chat is an instruction-following model finetuned on MBZUAI/MobiLlama-1B, aiming to meet the needs of resource-constrained devices.

🚀 Quick Start

We present MobiLlama-1.2B-Chat, an instruction following model finetuned on MBZUAI/MobiLlama-1B.

✨ Features

Model Summary

"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development. However, LLMs do not suit well for scenarios that require on-device processing, energy efficiency, low memory footprint, and response efficiency. These requisites are crucial for privacy, security, and sustainable deployment. This paper explores the ‘less is more’ paradigm by addressing the challenge of designing accurate yet efficient Small Language Models (SLMs) for resource-constrained devices. Our primary contribution is the introduction of an accurate and fully transparent open-source 0.5 billion (0.5B) parameter SLM, named MobiLlama, catering to the specific needs of resource-constrained computing with an emphasis on enhanced performance with reduced resource demands. MobiLlama is a SLM design that initiates from a larger model and applies a careful parameter sharing scheme to reduce both the pre-training and the deployment cost. Our work strives to not only bridge the gap in open-source SLMs but also ensures full transparency, where complete training data pipeline, training code, model weights, and over 300 checkpoints along with evaluation codes are available on our Github.

Arxiv Paper Link

Model Description

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MBZUAI/MobiLlama-1B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("MBZUAI/MobiLlama-1B-Chat", trust_remote_code=True)
model.to('cuda')

#template adapated from fastchat
template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"

prompt = "What are the key benefits of practicing mindfulness meditation?"

input_str = template.format(prompt=prompt)
input_ids = tokenizer(input_str, return_tensors="pt").to('cuda').input_ids
outputs = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())

Advanced Usage

Alternatively, you may use FastChat:

python3 -m fastchat.serve.cli --model-path MBZUAI/MobiLlama-1B-Chat

📚 Documentation

MobiLlama-1B-Chat Finetuning Details

DataMix

Hyperparameters

Evaluation

Citation

BibTeX:

@misc{thawakar2024mobillama,
      title={MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT}, 
      author={Omkar Thawakar and Ashmal Vayani and Salman Khan and Hisham Cholakkal and Rao Muhammad Anwer and Michael Felsberg and Timothy Baldwin and Eric P. Xing and Fahad Shahbaz Khan},
      year={2024},
      eprint={2402.16840},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
} 

📄 License

This project is licensed under the Apache 2.0 license.