Instructions to use shanyangmie/physics-r1-seed42-v4-step40-fsdp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shanyangmie/physics-r1-seed42-v4-step40-fsdp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="shanyangmie/physics-r1-seed42-v4-step40-fsdp")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shanyangmie/physics-r1-seed42-v4-step40-fsdp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use shanyangmie/physics-r1-seed42-v4-step40-fsdp with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shanyangmie/physics-r1-seed42-v4-step40-fsdp" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shanyangmie/physics-r1-seed42-v4-step40-fsdp", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/shanyangmie/physics-r1-seed42-v4-step40-fsdp
- SGLang
How to use shanyangmie/physics-r1-seed42-v4-step40-fsdp 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 "shanyangmie/physics-r1-seed42-v4-step40-fsdp" \ --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": "shanyangmie/physics-r1-seed42-v4-step40-fsdp", "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 "shanyangmie/physics-r1-seed42-v4-step40-fsdp" \ --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": "shanyangmie/physics-r1-seed42-v4-step40-fsdp", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use shanyangmie/physics-r1-seed42-v4-step40-fsdp with Docker Model Runner:
docker model run hf.co/shanyangmie/physics-r1-seed42-v4-step40-fsdp
Download data.pt from shanyangmie/physics-r1-seed42-v4-step40-fsdp: direct link, hf CLI and curl.
- Browser
- Download file 1.95 kB
-
https://huggingface.co/shanyangmie/physics-r1-seed42-v4-step40-fsdp/resolve/main/data.pt
- Command line
-
hf download hf://shanyangmie/physics-r1-seed42-v4-step40-fsdp/data.pt
-
curl -L -o data.pt https://huggingface.co/shanyangmie/physics-r1-seed42-v4-step40-fsdp/resolve/main/data.pt
1.95 kB
- Xet hash:
- c3d5099797bb87d6b5690c2edd1e0cfde7bbe686b9b3a17359eefe9744a381a0
- Size of remote file:
- 1.95 kB
- SHA256:
- 2fc5f5715a4d6c3997b93aece570c8d5a4a77570a3559d48f3b8ca5ba5f727b0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.