Instructions to use Azrail/smallm_70_rope with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Azrail/smallm_70_rope with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Azrail/smallm_70_rope", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Azrail/smallm_70_rope", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Azrail/smallm_70_rope with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Azrail/smallm_70_rope" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Azrail/smallm_70_rope", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Azrail/smallm_70_rope
- SGLang
How to use Azrail/smallm_70_rope 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 "Azrail/smallm_70_rope" \ --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": "Azrail/smallm_70_rope", "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 "Azrail/smallm_70_rope" \ --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": "Azrail/smallm_70_rope", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Azrail/smallm_70_rope with Docker Model Runner:
docker model run hf.co/Azrail/smallm_70_rope
Download model.safetensors from Azrail/smallm_70_rope: direct link, hf CLI and curl.
- Browser
- Download file 301 MB
-
https://huggingface.co/Azrail/smallm_70_rope/resolve/f02308be46a3fa732ce08ae205b9a0f01b99226b/model.safetensors
- Command line
-
hf download hf://Azrail/smallm_70_rope@f02308be46a3fa732ce08ae205b9a0f01b99226b/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/Azrail/smallm_70_rope/resolve/f02308be46a3fa732ce08ae205b9a0f01b99226b/model.safetensors
301 MB
- Xet hash:
- 1f6016d1bd0ed926a6a27c5ccf9338fe499766b897ddac3e0c4d8358f206508d
- Size of remote file:
- 301 MB
- SHA256:
- 0815144315751afde957889b3801664e381aaf78af5aaa224fc2449fb124f643
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.