54 lines
2.1 KiB
Markdown
54 lines
2.1 KiB
Markdown
---
|
||
license: apache-2.0
|
||
datasets:
|
||
- HuggingFaceFW/fineweb
|
||
language:
|
||
- en
|
||
library_name: transformers
|
||
tags:
|
||
- IoT
|
||
- sensor
|
||
- embedded
|
||
---
|
||
|
||
# TinyLLM
|
||
|
||
## Overview
|
||
|
||
This repository hosts a small language model developed as part of the TinyLLM framework ([arxiv link]). These models are specifically designed and fine-tuned with sensor data to support embedded sensing applications. They enable locally hosted language models on low-computing-power devices, such as single-board computers. The models, based on the GPT-2 architecture, are trained using Nvidia's H100 GPUs. This repo provides base models that can be further fine-tuned for specific downstream tasks related to embedded sensing.
|
||
## Model Information
|
||
|
||
- **Parameters:** 30M (Hidden Size = 384)
|
||
- **Architecture:** Decoder-only transformer
|
||
- **Training Data:** Up to 10B tokens from the [SHL](http://www.shl-dataset.org/) and [Fineweb](https://huggingface.co/datasets/HuggingFaceFW/fineweb) datasets, combined in a 4:6 ratio
|
||
- **Input and Output Modality:** Text
|
||
- **Context Length:** 1024
|
||
|
||
## Acknowledgements
|
||
|
||
We want to acknowledge the open-source frameworks [llm.c](https://github.com/karpathy/llm.c) and [llama.cpp](https://github.com/ggerganov/llama.cpp) and the sensor dataset provided by SHL, which were instrumental in training and testing these models.
|
||
|
||
## Usage
|
||
|
||
The model can be used in two primary ways:
|
||
1. **With Hugging Face’s Transformers Library**
|
||
```python
|
||
from transformers import pipeline
|
||
import torch
|
||
|
||
path = "tinyllm/30M-0.4"
|
||
prompt = "The sea is blue but it's his red sea"
|
||
|
||
generator = pipeline("text-generation", model=path,max_new_tokens = 30, repetition_penalty=1.3, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto")
|
||
print(generator(prompt)[0]['generated_text'])
|
||
```
|
||
|
||
2. **With llama.cpp**
|
||
Generate a GGUF model file using this [tool](https://github.com/ggerganov/llama.cpp/blob/master/convert_hf_to_gguf.py) and use the generated GGUF file for inferencing.
|
||
```python
|
||
python3 convert_hf_to_gguf.py models/mymodel/
|
||
```
|
||
|
||
## Disclaimer
|
||
|
||
This model is intended solely for research purposes. |