Instructions to use SauravP97/tiny-stories-3M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SauravP97/tiny-stories-3M with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SauravP97/tiny-stories-3M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SauravP97/tiny-stories-3M")
model = AutoModelForCausalLM.from_pretrained("SauravP97/tiny-stories-3M")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SauravP97/tiny-stories-3M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SauravP97/tiny-stories-3M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SauravP97/tiny-stories-3M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SauravP97/tiny-stories-3M

SGLang

How to use SauravP97/tiny-stories-3M with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SauravP97/tiny-stories-3M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SauravP97/tiny-stories-3M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SauravP97/tiny-stories-3M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SauravP97/tiny-stories-3M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SauravP97/tiny-stories-3M with Docker Model Runner:
```
docker model run hf.co/SauravP97/tiny-stories-3M
```

Model Card for Model ID

Model Details

This is a reproduction of a 3.6 million parameter language model from scratch by following the paper TinyStories: How Small Can Language Models Be and Still Speak Coherent English?. The goal of this project is to demostrate that a very small transformer model, when trained on a simpliefied synthetic dataset, can generate fluent, grammatically correct and consistent short stories.

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub.

Developed by: Saurav Prateek
Model type: Text Generationg (Transformer - Decoder model)
Parameters: 3.65 Million
Attention Layers: 8
Hidden Dimension: 64
Attention Heads per Layer: 16
Context Window: 512 tokens
Vocab Size: ~50K (GPT-Neo Tokenizer)
Learning Rate: 5e-4
Language(s) (NLP): English
License: MIT

Model Sources [optional]

Repository: https://github.com/SauravP97/tiny-stories-hf
Paper [optional]: https://arxiv.org/pdf/2305.07759

Training Details

Training Data

The model was trained on the TinyStories dataset, which consist of synthetic short stories generated by GPT-3.5/4. The stories use a restricted vocabulary typical of a 3-year-old child.

Source: Hugging Face Datasets (roneneldan/TinyStories)
Size: ~2GB text data

Training Procedure

The model was trained from scratch on a NVIDIA T4 GPU for around 3 hours to achieve a loss of 2.17. The model was trained for 0.22 epochs estimating around 55K steps. We used EleutherAI/gpt-neo-125M tokenizer model training and inference.

Training Hyperparameters

Training regime:
- Epochs: 0.22
- Loss: 2.17
- GPU: NVIDIA T4
- Training Steps: 55,000
- Training Time: ~3 hours

Citation [optional]

https://arxiv.org/abs/2305.07759

Downloads last month: 10

Safetensors

Model size

3.65M params

Tensor type

F32

Dataset used to train SauravP97/tiny-stories-3M

Paper for SauravP97/tiny-stories-3M

TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

Paper • 2305.07759 • Published May 12, 2023 • 45