Instructions to use OrionZheng/openmoe-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OrionZheng/openmoe-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OrionZheng/openmoe-base", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OrionZheng/openmoe-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OrionZheng/openmoe-base", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OrionZheng/openmoe-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OrionZheng/openmoe-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OrionZheng/openmoe-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OrionZheng/openmoe-base

SGLang

How to use OrionZheng/openmoe-base 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 "OrionZheng/openmoe-base" \
    --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": "OrionZheng/openmoe-base",
		"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 "OrionZheng/openmoe-base" \
        --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": "OrionZheng/openmoe-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OrionZheng/openmoe-base with Docker Model Runner:
```
docker model run hf.co/OrionZheng/openmoe-base
```

openmoe-base

Commit History

Update README.md

2195568
verified

OrionZheng commited on Jan 19, 2024

Update README.md

6cd42a8
verified

OrionZheng commited on Jan 16, 2024

Upload README.md

fde80f8
verified

OrionZheng commited on Jan 16, 2024

Update README.md

7bc671c
verified

OrionZheng commited on Jan 12, 2024

Update README.md

f69eb22
verified

OrionZheng commited on Jan 12, 2024

Update README.md

3da30d1
verified

OrionZheng commited on Jan 12, 2024

Upload README.md

f3171bc
verified

OrionZheng commited on Jan 12, 2024

Update colab_env.txt

3ccc470
verified

OrionZheng commited on Jan 11, 2024

Update prepare_env.sh

a22eba0
verified

OrionZheng commited on Jan 11, 2024

Update prepare_env.sh

a442273
verified

OrionZheng commited on Jan 11, 2024

Update README.md

7b380fc
verified

OrionZheng commited on Jan 10, 2024

Update README.md

56d9f12
verified

OrionZheng commited on Jan 10, 2024

Update README.md

306c455
verified

OrionZheng commited on Jan 10, 2024

Update README.md

ec74ec4
verified

OrionZheng commited on Jan 10, 2024

Upload 3 files

b9db556
verified

OrionZheng commited on Jan 10, 2024

Align bos_token_id with umt5

43447fe

OrionZheng commited on Dec 30, 2023

Align bos_token_id with umt5

8b07911

OrionZheng commited on Dec 30, 2023

Update config.json

e00ffd4

OrionZheng commited on Dec 30, 2023

Upload 2 files

1f9518c

OrionZheng commited on Dec 29, 2023

Update modeling_openmoe.py

d9ba731

OrionZheng commited on Dec 27, 2023