Mobillama 1B Chat

🚀 MobiLlama-1B-Chat

我們推出了 MobiLlama-1.2B-Chat，這是一個在 MBZUAI/MobiLlama-1B 基礎上微調的指令跟隨模型。它旨在滿足資源受限設備的特定需求，在降低資源需求的同時提升性能。

🚀 快速開始

加載 MobiLlama-1B-Chat

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())

或者，你可以使用 FastChat：

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

✨ 主要特性

在近期大語言模型（LLM）的發展中，“越大越好”一直是主流趨勢。然而，大語言模型並不適合需要設備端處理、能源效率、低內存佔用和響應效率的場景。這些要求對於隱私、安全和可持續部署至關重要。本文通過應對為資源受限設備設計準確且高效的小語言模型（SLM）這一挑戰，探索了“少即是多”的範式。我們的主要貢獻是推出了一個準確且完全透明的開源 5 億（0.5B）參數的小語言模型 MobiLlama，它滿足資源受限計算的特定需求，強調在降低資源需求的同時提升性能。MobiLlama 是一種小語言模型設計，它從一個更大的模型開始，並應用了一種謹慎的參數共享方案，以降低預訓練和部署成本。我們的工作不僅努力填補開源小語言模型的空白，還確保了完全透明，完整的訓練數據管道、訓練代碼、模型權重以及 300 多個檢查點和評估代碼都可以在我們的 Github 上找到。

Arxiv 論文鏈接

📚 詳細文檔

模型描述

MobiLlama-1B-Chat 微調詳情

DataMix

超參數

評估

引用

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}
} 

📄 許可證

本模型使用 Apache 2.0 許可證。