Instructions to use deepseek-ai/DeepSeek-Math-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-Math-V2 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-Math-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Math-V2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-Math-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-Math-V2"
# 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-Math-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-Math-V2

SGLang

How to use deepseek-ai/DeepSeek-Math-V2 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-Math-V2" \
    --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-Math-V2",
		"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-Math-V2" \
        --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-Math-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-Math-V2 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-Math-V2
```

DeepSeek-Math-V2 / inference /README.md

ZhihongShao

update README.md

9b04ba2 6 months ago

preview code

raw

history blame

783 Bytes

Inference code for DeepSeek models

First convert huggingface model weight files to the format of this project.

python convert.py --hf-ckpt-path ${HF_CKPT_PATH} --save-path ${SAVE_PATH} --n-experts ${EXPERTS} --model-parallel ${MP}

Then chat with DeepSeek model at will!

torchrun --nproc-per-node ${MP} generate.py --ckpt-path ${SAVE_PATH} --config ${CONFIG} --interactive --temperature {T}

Or batch inference from file.

torchrun --nproc-per-node ${MP} generate.py --ckpt-path ${SAVE_PATH} --config ${CONFIG} --input-file ${FILE}

Or multi nodes inference.

torchrun --nnodes ${NODES} --nproc-per-node $((MP / NODES)) --node-rank $RANK --master-addr $ADDR generate.py --ckpt-path ${SAVE_PATH} --config ${CONFIG} --input-file ${FILE}