Instructions to use Sigurdur/icechat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sigurdur/icechat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Sigurdur/icechat")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Sigurdur/icechat") model = AutoModelForCausalLM.from_pretrained("Sigurdur/icechat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Sigurdur/icechat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sigurdur/icechat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sigurdur/icechat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sigurdur/icechat
- SGLang
How to use Sigurdur/icechat 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 "Sigurdur/icechat" \ --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": "Sigurdur/icechat", "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 "Sigurdur/icechat" \ --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": "Sigurdur/icechat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Sigurdur/icechat with Docker Model Runner:
docker model run hf.co/Sigurdur/icechat
Download model.safetensors from Sigurdur/icechat: direct link, hf CLI and curl.
- Browser
- Download file 442 MB
-
https://huggingface.co/Sigurdur/icechat/resolve/main/model.safetensors
- Command line
-
hf download hf://Sigurdur/icechat/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/Sigurdur/icechat/resolve/main/model.safetensors
442 MB
- Xet hash:
- 4226d40e2371d29f4e4cb2c05d3df2cd8c9e451a1bb3cb0dac0338894ff4a802
- Size of remote file:
- 442 MB
- SHA256:
- 25f14a5aa2e41484cde36fef6495fba3fcb82495d2504b2dc425981b49754ac4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.