Instructions to use deepseek-ai/deepseek-moe-16b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-moe-16b-chat with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-moe-16b-chat", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-moe-16b-chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/deepseek-moe-16b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-moe-16b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-moe-16b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-moe-16b-chat

SGLang

How to use deepseek-ai/deepseek-moe-16b-chat 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 "deepseek-ai/deepseek-moe-16b-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-moe-16b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "deepseek-ai/deepseek-moe-16b-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-moe-16b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-moe-16b-chat with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-moe-16b-chat
```

Moe from your 7b param model would be more effective

by rombodawg - opened Jan 11, 2024

Discussion

rombodawg

Jan 11, 2024

I get that this is impressive because a 2.8b param models infrence speed can match 7b param models quality. But its not really practical. If you can run a 7b parameter model you dont really need the extra inference speed, what you need is better quality.

This is just my opinion, but I would have much preferred a bigger MoE from your guys made up from your 7b parameter models.
like a mixtral-48b param model but made up from deepseeklm-7b. Or even deepseekcoder-6.7b-instruct.

rombodawg

Jan 11, 2024

I was recently informed that the 40% in your github referred to training compute requirement needed not inference speed. Which in that case I kindoff take back what i said. This model does alot more than i though it did, considering you can probably fully train it on 24gb of vram in 4-bit using qlora with no issue.

But still i want to see that deepseek-48b-MoE please 😁

rombodawg

Jan 11, 2024

If im mistaken about anything I said here please correct me, so me and the community can better understand your model.
Cheers

ccYcc

Jan 11, 2024

i think this title can be changed as deepseeks-8*2.8b-chat

rombodawg

Jan 19, 2024

@deepseek-admin you guys took too long so i did it myself 😉

https://huggingface.co/rombodawg/deepseek-coder-moe_8x6.7b-base

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment