Instructions to use inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4") model = AutoModelForCausalLM.from_pretrained("inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4
- SGLang
How to use inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4 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 "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4" \ --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": "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4", "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 "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4" \ --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": "inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4 with Docker Model Runner:
docker model run hf.co/inswave/AISquare-Instruct-llama2-koen-13b-v0.9.4
- Xet hash:
- 3cd9c7a5efd939deedd78903ffc27bf35b0aa446496cce8b7058a579194c67aa
- Size of remote file:
- 1.64 GB
- SHA256:
- 97408a972a26e13e6d321c85039cf9d7cfeed96ae6ce21a8108cb71d5b2e134e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.