Instructions to use jetmoe/jetmoe-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jetmoe/jetmoe-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jetmoe/jetmoe-8b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jetmoe/jetmoe-8b") model = AutoModelForCausalLM.from_pretrained("jetmoe/jetmoe-8b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jetmoe/jetmoe-8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jetmoe/jetmoe-8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jetmoe/jetmoe-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jetmoe/jetmoe-8b
- SGLang
How to use jetmoe/jetmoe-8b 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 "jetmoe/jetmoe-8b" \ --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": "jetmoe/jetmoe-8b", "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 "jetmoe/jetmoe-8b" \ --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": "jetmoe/jetmoe-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jetmoe/jetmoe-8b with Docker Model Runner:
docker model run hf.co/jetmoe/jetmoe-8b
how to use it, any quick start guide
#3
by XavierShawn - opened
I loaded the model, is there some readme for me to try this out somehow?
it should be fine if you follow the code in the readme file, we are still waiting for transformers to accept our RP
after model = AutoModelForCausalLM.from_pretrained('jetmoe/jetmoe-8b')
now what to do? it would be nice to have a fully working readme for newbies, thanks.