Instructions to use osanseviero/sft_cml4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use osanseviero/sft_cml4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="osanseviero/sft_cml4")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("osanseviero/sft_cml4") model = AutoModelForCausalLM.from_pretrained("osanseviero/sft_cml4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use osanseviero/sft_cml4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "osanseviero/sft_cml4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "osanseviero/sft_cml4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/osanseviero/sft_cml4
- SGLang
How to use osanseviero/sft_cml4 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 "osanseviero/sft_cml4" \ --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": "osanseviero/sft_cml4", "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 "osanseviero/sft_cml4" \ --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": "osanseviero/sft_cml4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use osanseviero/sft_cml4 with Docker Model Runner:
docker model run hf.co/osanseviero/sft_cml4
Download pytorch_model.bin from osanseviero/sft_cml4: direct link, hf CLI and curl.
- Browser
- Download file 498 MB
-
https://huggingface.co/osanseviero/sft_cml4/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://osanseviero/sft_cml4/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/osanseviero/sft_cml4/resolve/main/pytorch_model.bin
498 MB
- Xet hash:
- 51a38da5f278a21cf04fdebbe371ca39be7b3c41cc4b7943393dc80a6d7d4d1e
- Size of remote file:
- 498 MB
- SHA256:
- ebad7d4e7fd700be342c7db7e91c93b7e35af759d45a4945f85fab4206a1055a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.