Instructions to use vitruv/vitruv_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vitruv/vitruv_1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vitruv/vitruv_1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("vitruv/vitruv_1") model = AutoModelForCausalLM.from_pretrained("vitruv/vitruv_1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use vitruv/vitruv_1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vitruv/vitruv_1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vitruv/vitruv_1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vitruv/vitruv_1
- SGLang
How to use vitruv/vitruv_1 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 "vitruv/vitruv_1" \ --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": "vitruv/vitruv_1", "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 "vitruv/vitruv_1" \ --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": "vitruv/vitruv_1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vitruv/vitruv_1 with Docker Model Runner:
docker model run hf.co/vitruv/vitruv_1
Who we are : Virtruv
ν΄λΉ λͺ¨λΈμ νκ΅μ΄ μ€ μν λͺ¨λΈμ μ§μ€νμ¬ νμ΅μ μλνμμ΅λλ€.
Base Model : 'beomi/OPEN-SOLAR-KO-10.7B'
Dataset : 1 . traintogpb/aihub-koen-translation-integrated-tiny-100k
kyujinpy/KOR-gugugu-platypus-set
GAIR/MathPile : λ€μ λ°μ΄ν° μ μ sampling νμ¬ μ§μ translate, νμμ΅λλ€.
Prompt:
- Downloads last month
- 72