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", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -105,7 +105,7 @@ Our training recipe follows the [MiniCPM](https://shengdinghu.notion.site/MiniCP
|
|
| 105 |
</figure>
|
| 106 |
|
| 107 |
## Technical Report
|
| 108 |
-
For more details, please refer to the JetMoE Technical Report
|
| 109 |
|
| 110 |
## JetMoE Model Index
|
| 111 |
|Model|Index|
|
|
|
|
| 105 |
</figure>
|
| 106 |
|
| 107 |
## Technical Report
|
| 108 |
+
For more details, please refer to the [JetMoE Technical Report](https://arxiv.org/abs/2404.07413).
|
| 109 |
|
| 110 |
## JetMoE Model Index
|
| 111 |
|Model|Index|
|