Instructions to use roneneldan/TinyStories-33M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roneneldan/TinyStories-33M with Transformers:

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

pipe = pipeline("text-generation", model="roneneldan/TinyStories-33M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("roneneldan/TinyStories-33M")
model = AutoModelForCausalLM.from_pretrained("roneneldan/TinyStories-33M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use roneneldan/TinyStories-33M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roneneldan/TinyStories-33M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roneneldan/TinyStories-33M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/roneneldan/TinyStories-33M

SGLang

How to use roneneldan/TinyStories-33M 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 "roneneldan/TinyStories-33M" \
    --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": "roneneldan/TinyStories-33M",
		"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 "roneneldan/TinyStories-33M" \
        --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": "roneneldan/TinyStories-33M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use roneneldan/TinyStories-33M with Docker Model Runner:
```
docker model run hf.co/roneneldan/TinyStories-33M
```

Correct maximum positional embeddings

#17

by nixgd - opened Jan 24, 2024

base: refs/heads/main

←

from: refs/pr/17

Discussion Files changed

-1

nixgd

Jan 24, 2024

The model appears to have been trained with context window = 512, not 2048 as claimed here. This can be seen by looking at the average loss by sequence position on the GPT4 tiny stories dataset (packed into inputs of length 2048):

It would be great to get this changed (for all tinystories models), as the current config is misleading.

Correct maximum positional embeddings97b72750

Corianas

Jan 25, 2024

You are quite correct, not sure what is up with the huggingface models as:
From the paper: OurmodelsareavailableonHuggingfacenamedTinyStories-1M/3M/9M/28M/33M/1Layer/2LayerandTinyStories-Instruct-∗.We use GPT-Neoarchitecturewithwindowsize256andcontext length512 .WeuseGPT-Neotokenizerbut only keep the top 10K most common tokens.

roneneldan

Owner Jan 25, 2024

You're right. Our paper does indicate that we use 512 seq len in training, but the model's config should be updated...

atyshka

Mar 16, 2024

@roneneldan Do you plan to merge this? I was also planning to contribute a version with the 10K vocab, would you consider merging that too or do you prefer the current format?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment