Instructions to use Mathoctopus/Cross_33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mathoctopus/Cross_33B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Mathoctopus/Cross_33B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Mathoctopus/Cross_33B") model = AutoModelForCausalLM.from_pretrained("Mathoctopus/Cross_33B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Mathoctopus/Cross_33B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mathoctopus/Cross_33B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Mathoctopus/Cross_33B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Mathoctopus/Cross_33B
- SGLang
How to use Mathoctopus/Cross_33B 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 "Mathoctopus/Cross_33B" \ --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": "Mathoctopus/Cross_33B", "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 "Mathoctopus/Cross_33B" \ --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": "Mathoctopus/Cross_33B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Mathoctopus/Cross_33B with Docker Model Runner:
docker model run hf.co/Mathoctopus/Cross_33B
- Xet hash:
- 4df537aab2cacb37d73a89dacbbe73f5b3227f1a1e560c332750b29611e1f733
- Size of remote file:
- 9.69 GB
- SHA256:
- 27c6d48a7e4e0ecbe1f450294bb610bb3a182568097c18aacc1d9f19b9c3a8a7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.