Instructions to use cloudyu/Mixtral_7Bx2_MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cloudyu/Mixtral_7Bx2_MoE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cloudyu/Mixtral_7Bx2_MoE")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cloudyu/Mixtral_7Bx2_MoE") model = AutoModelForCausalLM.from_pretrained("cloudyu/Mixtral_7Bx2_MoE") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use cloudyu/Mixtral_7Bx2_MoE with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cloudyu/Mixtral_7Bx2_MoE" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cloudyu/Mixtral_7Bx2_MoE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/cloudyu/Mixtral_7Bx2_MoE
- SGLang
How to use cloudyu/Mixtral_7Bx2_MoE 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 "cloudyu/Mixtral_7Bx2_MoE" \ --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": "cloudyu/Mixtral_7Bx2_MoE", "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 "cloudyu/Mixtral_7Bx2_MoE" \ --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": "cloudyu/Mixtral_7Bx2_MoE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use cloudyu/Mixtral_7Bx2_MoE with Docker Model Runner:
docker model run hf.co/cloudyu/Mixtral_7Bx2_MoE
Add MOE (mixture of experts) tag
#6 opened over 2 years ago
by
davanstrien
Problem with tokenizer
1
#4 opened over 2 years ago
by deleted
One or two models during inference?
3
#3 opened over 2 years ago
by
Venkman42
Can You Share Your Config
3
#2 opened over 2 years ago
by
Weyaxi
How to merge models into moe?
2
#1 opened over 2 years ago
by
Yhyu13