README.md

---
license: apache-2.0
datasets:
- mlfoundations/dclm-baseline-1.0-parquet
- bigcode/starcoderdata
- open-web-math/open-web-math
- allenai/dolma
language:
- en
library_name: transformers
---
PhoneLM-0.5B is a 0.5 billion parameter decoder-only language model pre-trained on 1.1 trillion tokens.

## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = 'mllmTeam/PhoneLM-0.5B'
model = AutoModelForCausalLM.from_pretrained(model_name, device_map='cuda', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name)

inp = tokenizer("Machine Learning is ", return_tensors="pt")
inp = {k: v.to('cuda') for k, v in inp.items()}
out = model.generate(**inp, 
                     max_length=256,
                     do_sample=True,
                     temperature=0.7,
                     top_p=0.7
                     )
text = tokenizer.decode(out[0], skip_special_tokens=True)
print(text)
```

## Model Details

* **Developed by**: mllmTeam
* **Model type**: `PhoneLM 0.5B` models are auto-regressive language models based on the transformer decoder architecture.
* **Language(s)**: English
* **Paper**: [PhoneLM Technical Report]()
* **Library**: [PhoneLM](https://github.com/UbiquitousLearning/PhoneLM)

### Model Architecture

The model is a decoder-only transformer architecture with the following modifications:

| Hidden Size | Layers | Heads | Sequence Length |
|-------------|--------|-------|-----------------|
| 1024        | 24     | 16    | 2048            |

* **Position Embeddings**: Rotary Position Embeddings ([Su et al., 2021](https://arxiv.org/abs/2104.09864)) applied to the first 25% of head embedding dimensions for improved throughput following [Black et al. (2022)](https://arxiv.org/pdf/2204.06745.pdf). PhoneLM quantized the sin and cos values in Rotary Position Embeddings to 8-bit integers.
* **Normalization**: LayerNorm ([Ba et al., 2016](https://arxiv.org/abs/1607.06450)) with learned bias terms as opposed to RMSNorm ([Zhang & Sennrich, 2019](https://arxiv.org/abs/1910.07467)).
* **Biases**: We remove all bias terms from the feed-forward networks and multi-head self-attention layers, except for the biases of the query, key, and value projections ([Bai et al., 2023](https://arxiv.org/abs/2309.16609)).
* **ReLU Activation Function**: ReLU([Glorot et al., 2011](https://proceedings.mlr.press/v15/glorot11a/glorot11a.pdf)) activation functions are adopted in feed-forward networks.
* **Tokenizer**: We use the SmolLM([Allal et al., 2024](https://huggingface.co/blog/smollm))'s tokenizer with a vocabulary size of 49,152. 

## Training Dataset

The training dataset PhoneLM used is comprised of a filtered mixture of open-source large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets): DCLM-baseline([Li et al., 2024](https://arxiv.org/abs/2406.11794)), StarCoder ([Li et al., 2023](https://arxiv.org/abs/2305.06161)), OpenWebMath ([Paster et al., 2023](https://arxiv.org/abs/2310.06786)) and Dolma ([Soldaini et al., 2024](https://aclanthology.org/2024.acl-long.840/)).

## Evaluation Results
| Model | HellaSwag | WinoGrande | PIQA | SciQ | BoolQ | ARC Easy | ARC Challenge | Average |
|-----------|-----------|------------|------|------|-------|----------|---------------|---------|
| **PhoneLM-0.5B** | **54.0** | **57.9** | **73.3** | **85.1** | **60.7** | **60.4** | **31.6** | **60.43** |
| Pythia-410M | 40.6 | 53.7 | 66.9 | 72.4 | 60.3 | 45.9 | 24.5 | 52.04 |
| OPT-350M | 36.8 | 52.3 | 64.3 | 68.5 | 57.6 | 40.1 | 23.7 | 49.04 |
| BLOOM-560M | 36.9 | 51.7 | 65.0 | 71.7 | 53.3 | 41.8 | 23.7 | 49.16 |
| MobiLlama-500M | 51.1 | 53.4 | 70.9 | 76.4 | 55.7 | 46.0 | 26.6 | 54.30 |
| OpenELM-450M | 54.0 | 58.0 | 72.3 | 79.4 | 55.8 | 48.1 | 27.6 | 56.46 |
| SmolLM-360M | 53.5 | 56.8 | 71.5 | 84.2 | 55.4 | 63.8 | 36.0 | 60.17 |
| Qwen 1.5-500M | 49.2 | 55.7 | 69.5 | 82.5 | 49.5 | 52.3 | 29.4 | 55.44 |
| Cerebras-GPT-590M | 32.3 | 49.8 | 62.8 | 68.2 | 59.2 | 41.2 | 23.5 | 48.14 |

## License
* This repository is released under the [Apache-2.0](https://huggingface.co/mllmTeam/PhoneLM-0.5B/blob/main/README.md) License.


## Citation
```
@misc{yi2024phonelmanefficientcapablesmall,
      title={PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training}, 
      author={Rongjie Yi and Xiang Li and Weikai Xie and Zhenyan Lu and Chenghua Wang and Ao Zhou and Shangguang Wang and Xiwen Zhang and Mengwei Xu},
      year={2024},
      eprint={2411.05046},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2411.05046}, 
}
```