Instructions to use nikokons/gpt2-greek with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nikokons/gpt2-greek with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nikokons/gpt2-greek")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nikokons/gpt2-greek") model = AutoModelForCausalLM.from_pretrained("nikokons/gpt2-greek", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nikokons/gpt2-greek with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nikokons/gpt2-greek" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nikokons/gpt2-greek", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nikokons/gpt2-greek
- SGLang
How to use nikokons/gpt2-greek 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 "nikokons/gpt2-greek" \ --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": "nikokons/gpt2-greek", "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 "nikokons/gpt2-greek" \ --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": "nikokons/gpt2-greek", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nikokons/gpt2-greek with Docker Model Runner:
docker model run hf.co/nikokons/gpt2-greek
Download pytorch_model.bin from nikokons/gpt2-greek: direct link, hf CLI and curl.
- Browser
- Download file 422 MB
-
https://huggingface.co/nikokons/gpt2-greek/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://nikokons/gpt2-greek/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/nikokons/gpt2-greek/resolve/main/pytorch_model.bin
422 MB
- Xet hash:
- 017109cdca0b40df079b255a5dac1f7572d57e34d2e5b6baaf7d40bca0042078
- Size of remote file:
- 422 MB
- SHA256:
- a0bc5fb444ffe220d94afb3e26515970f42dea15f33848dad80d30e4752ad686
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.