🚀 MobiLlama-1B-Chat
我们推出了 MobiLlama-1.2B-Chat,这是一个在 MBZUAI/MobiLlama-1B 基础上微调的指令跟随模型。它旨在满足资源受限设备的特定需求,在降低资源需求的同时提升性能。
🚀 快速开始
加载 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= "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
在近期大语言模型(LLM)的发展中,“越大越好”一直是主流趋势。然而,大语言模型并不适合需要设备端处理、能源效率、低内存占用和响应效率的场景。这些要求对于隐私、安全和可持续部署至关重要。本文通过应对为资源受限设备设计准确且高效的小语言模型(SLM)这一挑战,探索了“少即是多”的范式。我们的主要贡献是推出了一个准确且完全透明的开源 5 亿(0.5B)参数的小语言模型 MobiLlama,它满足资源受限计算的特定需求,强调在降低资源需求的同时提升性能。MobiLlama 是一种小语言模型设计,它从一个更大的模型开始,并应用了一种谨慎的参数共享方案,以降低预训练和部署成本。我们的工作不仅努力填补开源小语言模型的空白,还确保了完全透明,完整的训练数据管道、训练代码、模型权重以及 300 多个检查点和评估代码都可以在我们的 Github 上找到。
Arxiv 论文链接
📚 详细文档
模型描述
MobiLlama-1B-Chat 微调详情
DataMix
子集 |
行数 |
许可证 |
WizardLM/WizardLM_evol_instruct_V2_196k |
143k |
|
icybee/share_gpt_90k_v1 |
90k |
cc0 - 1.0 |
总计 |
233k |
|
超参数
超参数 |
值 |
总参数 |
1.2B |
隐藏层大小 |
2048 |
中间层大小(MLPs) |
5632 |
注意力头数量 |
32 |
隐藏层数量 |
22 |
RMSNorm ɛ |
1e^ - 5 |
最大序列长度 |
2048 |
词表大小 |
32000 |
训练超参数 |
值 |
学习率 |
2e - 5 |
训练轮数 |
3 |
每个设备的训练批次大小 |
2 |
梯度累积步数 |
16 |
热身比例 |
0.04 |
模型最大长度 |
2048 |
评估
评估基准 |
MobiLlama - 05B - Chat |
MobiLlama - 1.2B - Chat |
HellaSwag |
0.5042 |
0.6244 |
MMLU |
0.2677 |
0.2635 |
Arc Challenge |
0.2935 |
0.3558 |
TruthfulQA |
0.3997 |
0.3848 |
CrowsPairs |
0.5694 |
0.679 |
PIQA |
0.7078 |
0.7557 |
Race |
0.3320 |
0.3598 |
SIQA |
0.4165 |
0.4396 |
Winogrande |
0.5659 |
0.5966 |
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}
}
📄 许可证
本模型使用 Apache 2.0 许可证。