Instructions to use goldfish-models/arb_arab_10mb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use goldfish-models/arb_arab_10mb with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="goldfish-models/arb_arab_10mb")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("goldfish-models/arb_arab_10mb") model = AutoModelForCausalLM.from_pretrained("goldfish-models/arb_arab_10mb") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use goldfish-models/arb_arab_10mb with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "goldfish-models/arb_arab_10mb" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "goldfish-models/arb_arab_10mb", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/goldfish-models/arb_arab_10mb
- SGLang
How to use goldfish-models/arb_arab_10mb 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 "goldfish-models/arb_arab_10mb" \ --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": "goldfish-models/arb_arab_10mb", "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 "goldfish-models/arb_arab_10mb" \ --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": "goldfish-models/arb_arab_10mb", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use goldfish-models/arb_arab_10mb with Docker Model Runner:
docker model run hf.co/goldfish-models/arb_arab_10mb
- Xet hash:
- a17337683013fc4fd31bfe1cd78ca2f23d825519d19720812d8148056cf15e34
- Size of remote file:
- 157 MB
- SHA256:
- 504f3109b680e7a2c7b09fd6ba579d7646334726f7069e1b8b2ac6d2369aba7f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.