Instructions to use empushy/gpt2-emulator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use empushy/gpt2-emulator with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="empushy/gpt2-emulator")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("empushy/gpt2-emulator") model = AutoModelForCausalLM.from_pretrained("empushy/gpt2-emulator", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use empushy/gpt2-emulator with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "empushy/gpt2-emulator" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "empushy/gpt2-emulator", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/empushy/gpt2-emulator
- SGLang
How to use empushy/gpt2-emulator 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 "empushy/gpt2-emulator" \ --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": "empushy/gpt2-emulator", "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 "empushy/gpt2-emulator" \ --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": "empushy/gpt2-emulator", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use empushy/gpt2-emulator with Docker Model Runner:
docker model run hf.co/empushy/gpt2-emulator
Download training_args.bin from empushy/gpt2-emulator: direct link, hf CLI and curl.
- Browser
- Download file 2.35 kB
-
https://huggingface.co/empushy/gpt2-emulator/resolve/main/training_args.bin
- Command line
-
hf download hf://empushy/gpt2-emulator/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/empushy/gpt2-emulator/resolve/main/training_args.bin
2.35 kB
- Xet hash:
- a5e9b604baec291d07989a03110ef0af42bd8316e91844530a9017303a7c94bd
- Size of remote file:
- 2.35 kB
- SHA256:
- e1b65e46c37193b61039559f5d3a3c73dbb95ab3dc845c86cc37ed12a94db83c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.