Instructions to use agnavale/raphael with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use agnavale/raphael with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="agnavale/raphael")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("agnavale/raphael") model = AutoModelForSeq2SeqLM.from_pretrained("agnavale/raphael", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use agnavale/raphael with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "agnavale/raphael" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "agnavale/raphael", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/agnavale/raphael
- SGLang
How to use agnavale/raphael 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 "agnavale/raphael" \ --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": "agnavale/raphael", "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 "agnavale/raphael" \ --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": "agnavale/raphael", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use agnavale/raphael with Docker Model Runner:
docker model run hf.co/agnavale/raphael
Download model.safetensors from agnavale/raphael: direct link, hf CLI and curl.
- Browser
- Download file 1.46 GB
-
https://huggingface.co/agnavale/raphael/resolve/main/model.safetensors
- Command line
-
hf download hf://agnavale/raphael/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/agnavale/raphael/resolve/main/model.safetensors
1.46 GB
- Xet hash:
- 73623bea85f10c9d86c929c4d41e4ada442e7df24cf22a65ac9a03c127b40ac3
- Size of remote file:
- 1.46 GB
- SHA256:
- a40af3f8b747d05153d71423678cac32406b9f599e199166f006bad783511762
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.