Instructions to use DarwinAnim8or/gpt2-124M-tinystories with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarwinAnim8or/gpt2-124M-tinystories with Transformers:

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

pipe = pipeline("text-generation", model="DarwinAnim8or/gpt2-124M-tinystories")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DarwinAnim8or/gpt2-124M-tinystories")
model = AutoModelForCausalLM.from_pretrained("DarwinAnim8or/gpt2-124M-tinystories", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DarwinAnim8or/gpt2-124M-tinystories with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DarwinAnim8or/gpt2-124M-tinystories"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarwinAnim8or/gpt2-124M-tinystories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DarwinAnim8or/gpt2-124M-tinystories

SGLang

How to use DarwinAnim8or/gpt2-124M-tinystories 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 "DarwinAnim8or/gpt2-124M-tinystories" \
    --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": "DarwinAnim8or/gpt2-124M-tinystories",
		"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 "DarwinAnim8or/gpt2-124M-tinystories" \
        --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": "DarwinAnim8or/gpt2-124M-tinystories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DarwinAnim8or/gpt2-124M-tinystories with Docker Model Runner:
```
docker model run hf.co/DarwinAnim8or/gpt2-124M-tinystories
```

GPT2-124M-TinyStories

This is a prototype / proof of concept model to see what the results of pretraining GPT2 exclusively on narrative texts would look like. That's right-- this isn't a finetune, it's entirely pretrained on TinyStories.

The GPT2 config and tokenizer is however unmodified from the original.

Downloads last month: 239

Safetensors

Model size

0.1B params

Tensor type

F32

DarwinAnim8or
/

gpt2-124M-tinystories

GPT2-124M-TinyStories

Dataset used to train DarwinAnim8or/gpt2-124M-tinystories