Instructions to use digitous/GPT-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/GPT-R with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/GPT-R")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/GPT-R") model = AutoModelForCausalLM.from_pretrained("digitous/GPT-R", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use digitous/GPT-R with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/GPT-R" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/GPT-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/GPT-R
- SGLang
How to use digitous/GPT-R 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 "digitous/GPT-R" \ --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": "digitous/GPT-R", "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 "digitous/GPT-R" \ --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": "digitous/GPT-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/GPT-R with Docker Model Runner:
docker model run hf.co/digitous/GPT-R
Download pytorch_model-00001-of-00006.bin from digitous/GPT-R: direct link, hf CLI and curl.
- Browser
- Download file 2.08 GB
-
https://huggingface.co/digitous/GPT-R/resolve/main/pytorch_model-00001-of-00006.bin
- Command line
-
hf download hf://digitous/GPT-R/pytorch_model-00001-of-00006.bin
-
curl -L -o pytorch_model-00001-of-00006.bin https://huggingface.co/digitous/GPT-R/resolve/main/pytorch_model-00001-of-00006.bin
2.08 GB
- Xet hash:
- deded25bf9ab78608c0446f667f6dddfed7d7d74f5ed2e51a4d135579b07f440
- Size of remote file:
- 2.08 GB
- SHA256:
- afcbcdb9e4a5f2a1ae7d92e0efecc0faba2911fb3429a049b499810d08d0f027
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.