Text Generation
Transformers
PyTorch
TensorFlow
Japanese
gpt2
japanese
lm
nlp
text-generation-inference
Instructions to use abeja/gpt2-large-japanese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abeja/gpt2-large-japanese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="abeja/gpt2-large-japanese")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("abeja/gpt2-large-japanese") model = AutoModelForCausalLM.from_pretrained("abeja/gpt2-large-japanese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use abeja/gpt2-large-japanese with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "abeja/gpt2-large-japanese" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abeja/gpt2-large-japanese", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/abeja/gpt2-large-japanese
- SGLang
How to use abeja/gpt2-large-japanese 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 "abeja/gpt2-large-japanese" \ --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": "abeja/gpt2-large-japanese", "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 "abeja/gpt2-large-japanese" \ --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": "abeja/gpt2-large-japanese", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use abeja/gpt2-large-japanese with Docker Model Runner:
docker model run hf.co/abeja/gpt2-large-japanese
Download pytorch_model.bin from abeja/gpt2-large-japanese: direct link, hf CLI and curl.
- Browser
- Download file 3.04 GB
-
https://huggingface.co/abeja/gpt2-large-japanese/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://abeja/gpt2-large-japanese/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/abeja/gpt2-large-japanese/resolve/main/pytorch_model.bin
3.04 GB
- Xet hash:
- c1133a9028f74d45468d39cd39c5b2c7b0f5e441d6514786705eceb0b4c42aac
- Size of remote file:
- 3.04 GB
- SHA256:
- eb5575dce810c32790f2806f28d1813627a7d55d6df6e378ab15b313c0365481
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.