Instructions to use felixhusen/scientific with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use felixhusen/scientific with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="felixhusen/scientific")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("felixhusen/scientific") model = AutoModelForCausalLM.from_pretrained("felixhusen/scientific", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use felixhusen/scientific with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "felixhusen/scientific" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "felixhusen/scientific", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/felixhusen/scientific
- SGLang
How to use felixhusen/scientific 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 "felixhusen/scientific" \ --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": "felixhusen/scientific", "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 "felixhusen/scientific" \ --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": "felixhusen/scientific", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use felixhusen/scientific with Docker Model Runner:
docker model run hf.co/felixhusen/scientific
Download tokenizer_config.json from felixhusen/scientific: direct link, hf CLI and curl.
- Browser
- Download file 155 Bytes
-
https://huggingface.co/felixhusen/scientific/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://felixhusen/scientific/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/felixhusen/scientific/resolve/main/tokenizer_config.json
155 Bytes
| {"do_lower_case": false, "model_max_length": 1024, "special_tokens_map_file": "models/scientific-out/special_tokens_map.json", "full_tokenizer_file": null} |