Text Generation
Transformers
Safetensors
English
gpt2
scaling-study
benchmarking
banterhearts
text-generation-inference
Instructions to use Crusadersk/gpt2-25m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Crusadersk/gpt2-25m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Crusadersk/gpt2-25m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Crusadersk/gpt2-25m") model = AutoModelForCausalLM.from_pretrained("Crusadersk/gpt2-25m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Crusadersk/gpt2-25m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Crusadersk/gpt2-25m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Crusadersk/gpt2-25m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Crusadersk/gpt2-25m
- SGLang
How to use Crusadersk/gpt2-25m 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 "Crusadersk/gpt2-25m" \ --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": "Crusadersk/gpt2-25m", "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 "Crusadersk/gpt2-25m" \ --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": "Crusadersk/gpt2-25m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Crusadersk/gpt2-25m with Docker Model Runner:
docker model run hf.co/Crusadersk/gpt2-25m
Download model.safetensors from Crusadersk/gpt2-25m: direct link, hf CLI and curl.
- Browser
- Download file 100 MB
-
https://huggingface.co/Crusadersk/gpt2-25m/resolve/main/model.safetensors
- Command line
-
hf download hf://Crusadersk/gpt2-25m/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/Crusadersk/gpt2-25m/resolve/main/model.safetensors
100 MB
- Xet hash:
- b51bfbeb89e48c0006ddbf90ba5d248544ea7d8d218fc3ebc8ca668d78b4d18e
- Size of remote file:
- 100 MB
- SHA256:
- da3b2fbc76d1fa1122cfd00415dfacc7d6302016646608a8396f3244854280d9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.