Sponsored by
YouArt
MBZUAI / MobiLlama-05B
Model's Last Updated: February 28 2024
text-generation
Introduction of MobiLlama-05B
Model Details of MobiLlama-05B
MobiLlama-05B
MobiLlama-05B is a Small Language Model with 0.5 billion parameters. It was trained using the Amber data sources Amber-Dataset .
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 .
Model Description
- Model type: Small Language Model (SLM) built using the architecture design of LLaMA-7B
- Language(s) (NLP): English
- License: Apache 2.0
- Resources for more information:
How to Use
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("MBZUAI/MobiLlama-05B", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("MBZUAI/MobiLlama-05B", trust_remote_code=True)
model.to('cuda')
text = "I was walking towards the river when "
input_ids = tokenizer(text, return_tensors="pt").to('cuda').input_ids
outputs = model.generate(input_ids, max_length=1000, repetition_penalty=1.2, pad_token_id=tokenizer.eos_token_id)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
Training DataMix
| Subset | Tokens (Billion) |
|---|---|
| Arxiv | 30.00 |
| Book | 28.86 |
| C4 | 197.67 |
| Refined-Web | 665.01 |
| StarCoder | 291.92 |
| StackExchange | 21.75 |
| Wikipedia | 23.90 |
| Total | 1259.13 |
Hyperparameters
| Hyperparameter | Value |
|---|---|
| Total Parameters | 0.52B |
| Hidden Size | 2048 |
| Intermediate Size (MLPs) | 5632 |
| Number of Attention Heads | 32 |
| Number of Hidden Lyaers | 22 |
| RMSNorm ɛ | 1e^-5 |
| Max Seq Length | 2048 |
| Vocab Size | 32000 |
Evaluation
| Evaluation Benchmark | MobiLlama-0.5B | MobiLlama-0.8B | MobiLlama-1.2B |
|---|---|---|---|
| HellaSwag | 52.52 | 54.09 | 62.99 |
| MMLU | 26.45 | 26.92 | 24.23 |
| Arc Challenge | 29.52 | 30.20 | 34.55 |
| TruthfulQA | 38.05 | 38.48 | 35.57 |
| CrowsPairs | 64.03 | 64.82 | 68.12 |
| PIQA | 72.03 | 73.17 | 75.29 |
| Race | 33.68 | 33.37 | 35.31 |
| SIQA | 40.22 | 41.60 | 41.96 |
| Winogrande | 57.53 | 57.45 | 61.08 |
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}
}
Runs of MBZUAI MobiLlama-05B on huggingface.co
916
Total runs
0
24-hour runs
20
3-day runs
86
7-day runs
242
30-day runs
More Information About MobiLlama-05B huggingface.co Model
Url of MobiLlama-05B
MobiLlama-05B huggingface.co Url
Provider of MobiLlama-05B huggingface.co
Other API from MBZUAI
Total runs:
2.6K
Run Growth:
-2.6K
Growth Rate:
-98.22%
Total runs:
1.7K
Run Growth:
-385
Growth Rate:
-23.05%
Total runs:
1.3K
Run Growth:
-7
Growth Rate:
-0.53%
Total runs:
1.1K
Run Growth:
-1.4K
Growth Rate:
-126.49%
Total runs:
1.1K
Run Growth:
-1.2K
Growth Rate:
-110.15%
Total runs:
916
Run Growth:
-1.2K
Growth Rate:
-133.30%
Total runs:
824
Run Growth:
329
Growth Rate:
39.93%
Total runs:
783
Run Growth:
783
Growth Rate:
100.00%
Total runs:
521
Run Growth:
-145
Growth Rate:
-26.46%
Total runs:
475
Run Growth:
-67
Growth Rate:
-14.11%
Total runs:
431
Run Growth:
83
Growth Rate:
19.26%
Total runs:
264
Run Growth:
-1.1K
Growth Rate:
-410.39%
Total runs:
210
Run Growth:
135
Growth Rate:
64.29%
Total runs:
192
Run Growth:
47
Growth Rate:
24.48%
Total runs:
156
Run Growth:
-1.6K
Growth Rate:
-1019.87%
Total runs:
142
Run Growth:
39
Growth Rate:
27.46%
Total runs:
107
Run Growth:
18
Growth Rate:
16.82%
Total runs:
56
Run Growth:
-53
Growth Rate:
-94.64%
Total runs:
35
Run Growth:
10
Growth Rate:
28.57%
Total runs:
34
Run Growth:
10
Growth Rate:
29.41%
Total runs:
26
Run Growth:
6
Growth Rate:
23.08%
Total runs:
25
Run Growth:
8
Growth Rate:
32.00%
Total runs:
22
Run Growth:
10
Growth Rate:
45.45%
Total runs:
21
Run Growth:
10
Growth Rate:
47.62%
Total runs:
21
Run Growth:
8
Growth Rate:
38.10%
Total runs:
16
Run Growth:
4
Growth Rate:
25.00%
Total runs:
16
Run Growth:
6
Growth Rate:
37.50%
Total runs:
12
Run Growth:
2
Growth Rate:
16.67%
Total runs:
12
Run Growth:
3
Growth Rate:
25.00%
Total runs:
10
Run Growth:
-18
Growth Rate:
-180.00%
Total runs:
8
Run Growth:
-2
Growth Rate:
-25.00%
Total runs:
8
Run Growth:
2
Growth Rate:
25.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
-2
Growth Rate:
-28.57%
Total runs:
7
Run Growth:
-4
Growth Rate:
-57.14%
Total runs:
4
Run Growth:
-3
Growth Rate:
-75.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%