Instructions to use karpathy/gpt2_1558M_final2_hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use karpathy/gpt2_1558M_final2_hf with Transformers:

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

pipe = pipeline("text-generation", model="karpathy/gpt2_1558M_final2_hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("karpathy/gpt2_1558M_final2_hf")
model = AutoModelForCausalLM.from_pretrained("karpathy/gpt2_1558M_final2_hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use karpathy/gpt2_1558M_final2_hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "karpathy/gpt2_1558M_final2_hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "karpathy/gpt2_1558M_final2_hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/karpathy/gpt2_1558M_final2_hf

SGLang

How to use karpathy/gpt2_1558M_final2_hf 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 "karpathy/gpt2_1558M_final2_hf" \
    --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": "karpathy/gpt2_1558M_final2_hf",
		"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 "karpathy/gpt2_1558M_final2_hf" \
        --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": "karpathy/gpt2_1558M_final2_hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use karpathy/gpt2_1558M_final2_hf with Docker Model Runner:
```
docker model run hf.co/karpathy/gpt2_1558M_final2_hf
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

This is a GPT-2 model trained in llm.c, for 32K steps (of 1M batch size) on FineWeb-EDU.

A lot more detailed information is here: https://github.com/karpathy/llm.c/discussions/677

Bias, Risks, and Limitations

Eagerly generates disinformation about English-speaking unicorns in the Andes mountains.

Downloads last month: 108

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for karpathy/gpt2_1558M_final2_hf

Quantizations

2 models

karpathy
/

gpt2_1558M_final2_hf

Model Card for Model ID

Bias, Risks, and Limitations

Model tree for karpathy/gpt2_1558M_final2_hf

Space using karpathy/gpt2_1558M_final2_hf 1