Instructions to use Sigurdur/jonas-hallgrimsson-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sigurdur/jonas-hallgrimsson-gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="Sigurdur/jonas-hallgrimsson-gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sigurdur/jonas-hallgrimsson-gpt2")
model = AutoModelForCausalLM.from_pretrained("Sigurdur/jonas-hallgrimsson-gpt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Sigurdur/jonas-hallgrimsson-gpt2 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Sigurdur/jonas-hallgrimsson-gpt2

SGLang

How to use Sigurdur/jonas-hallgrimsson-gpt2 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 "Sigurdur/jonas-hallgrimsson-gpt2" \
    --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": "Sigurdur/jonas-hallgrimsson-gpt2",
		"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 "Sigurdur/jonas-hallgrimsson-gpt2" \
        --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": "Sigurdur/jonas-hallgrimsson-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sigurdur/jonas-hallgrimsson-gpt2 with Docker Model Runner:
```
docker model run hf.co/Sigurdur/jonas-hallgrimsson-gpt2
```

jonas hallgrimsson gpt v2

second version of a gpt model trained on the works of Jónas Hallgrímsson. The model started heavilly overfitting, due to small training data, as the training metrics evidently show. Hence, this is model is an early checkpoint from the training (before the overfitting of the model)

Downloads last month: 11

Safetensors

Model size

0.1B params

Tensor type

F32

Sigurdur
/

jonas-hallgrimsson-gpt2

jonas hallgrimsson gpt v2

Dataset used to train Sigurdur/jonas-hallgrimsson-gpt2