Instructions to use OrionZheng/openmoe-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OrionZheng/openmoe-8b with Transformers:

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

pipe = pipeline("text-generation", model="OrionZheng/openmoe-8b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OrionZheng/openmoe-8b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OrionZheng/openmoe-8b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OrionZheng/openmoe-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OrionZheng/openmoe-8b"
# 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-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OrionZheng/openmoe-8b

SGLang

How to use OrionZheng/openmoe-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 "OrionZheng/openmoe-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": "OrionZheng/openmoe-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 "OrionZheng/openmoe-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": "OrionZheng/openmoe-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OrionZheng/openmoe-8b with Docker Model Runner:
```
docker model run hf.co/OrionZheng/openmoe-8b
```

OrionZheng commited on Jan 19, 2024

Commit

6806c15

verified ·

1 Parent(s): c683b2d

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ The table below lists the 8B/8B-Chat model that has completed training on 1.1T t
 | Model Name     | Description                      | #Param   |Huggingface |
 |----------------|-------------------------------------------------|----------|-------------|
-| **OpenMoE-8B(1.1T)**   | 8B MoE with comparable FLOPs of a 1.6B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b) |
 | **OpenMoE-8B-Chat (1.1T+SFT)**   | OpenMoE-8B-1.1T supervised finetuned on the [WildChat GPT-4 Subset](https://huggingface.co/datasets/allenai/WildChat-nontoxic)   |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-chat) |
@@ -34,11 +34,11 @@ Besides, we also provide all our intermediate checkpoints(base, 8B, 34B) for res
 | Model Name     | Description                      | #Param   |Huggingface |
 |----------------|-------------------------------------------------|----------|-------------|
 | **OpenMoE-34B-200B**   |  34B MoE with comparable FLOPs of a 7B LLaMA(No SFT)  |34B        |[Link](https://huggingface.co/OrionZheng/openmoe-34b-200B) |
-| OpenMoE-8B-200B   | 8B MoE with comparable FLOPs of a 1.6B LLaMA(No SFT) |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-200B) |
-| OpenMoE-8B-400B   | 8B MoE with comparable FLOPs of a 1.6B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-400B) |
-| OpenMoE-8B-600B   | 8B MoE with comparable FLOPs of a 1.6B LLaMA(No SFT) |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-600B) |
-| OpenMoE-8B-800B   | 8B MoE with comparable FLOPs of a 1.6B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-800B) |
-| OpenMoE-8B-1T   | 8B MoE with comparable FLOPs of a 1.6B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-1T) |
 | OpenMoE-base(128B)   | A small MoE model for debugging only       |637M      |[Link](https://huggingface.co/OrionZheng/openmoe-base) |
 | OpenLLaMA-base(128B) | A dense counter-part of OpenMoE-base            |310M      |[Link](https://huggingface.co/fuzhao/OpenLLaMA_Base) |

 | Model Name     | Description                      | #Param   |Huggingface |
 |----------------|-------------------------------------------------|----------|-------------|
+| **OpenMoE-8B(1.1T)**   | 8B MoE with comparable FLOPs of a 2B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b) |
 | **OpenMoE-8B-Chat (1.1T+SFT)**   | OpenMoE-8B-1.1T supervised finetuned on the [WildChat GPT-4 Subset](https://huggingface.co/datasets/allenai/WildChat-nontoxic)   |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-chat) |
 | Model Name     | Description                      | #Param   |Huggingface |
 |----------------|-------------------------------------------------|----------|-------------|
 | **OpenMoE-34B-200B**   |  34B MoE with comparable FLOPs of a 7B LLaMA(No SFT)  |34B        |[Link](https://huggingface.co/OrionZheng/openmoe-34b-200B) |
+| OpenMoE-8B-200B   | 8B MoE with comparable FLOPs of a 2B LLaMA(No SFT) |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-200B) |
+| OpenMoE-8B-400B   | 8B MoE with comparable FLOPs of a 2B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-400B) |
+| OpenMoE-8B-600B   | 8B MoE with comparable FLOPs of a 2B LLaMA(No SFT) |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-600B) |
+| OpenMoE-8B-800B   | 8B MoE with comparable FLOPs of a 2B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-800B) |
+| OpenMoE-8B-1T   | 8B MoE with comparable FLOPs of a 2B LLaMA(No SFT)  |8B        |[Link](https://huggingface.co/OrionZheng/openmoe-8b-1T) |
 | OpenMoE-base(128B)   | A small MoE model for debugging only       |637M      |[Link](https://huggingface.co/OrionZheng/openmoe-base) |
 | OpenLLaMA-base(128B) | A dense counter-part of OpenMoE-base            |310M      |[Link](https://huggingface.co/fuzhao/OpenLLaMA_Base) |