Instructions to use leylaparisdev/DeepSeek-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leylaparisdev/DeepSeek-V3.2 with Transformers:

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

pipe = pipeline("text-generation", model="leylaparisdev/DeepSeek-V3.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("leylaparisdev/DeepSeek-V3.2")
model = AutoModelForCausalLM.from_pretrained("leylaparisdev/DeepSeek-V3.2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use leylaparisdev/DeepSeek-V3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leylaparisdev/DeepSeek-V3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leylaparisdev/DeepSeek-V3.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/leylaparisdev/DeepSeek-V3.2

SGLang

How to use leylaparisdev/DeepSeek-V3.2 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 "leylaparisdev/DeepSeek-V3.2" \
    --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": "leylaparisdev/DeepSeek-V3.2",
		"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 "leylaparisdev/DeepSeek-V3.2" \
        --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": "leylaparisdev/DeepSeek-V3.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use leylaparisdev/DeepSeek-V3.2 with Docker Model Runner:
```
docker model run hf.co/leylaparisdev/DeepSeek-V3.2
```

DeepSeek-V3.2 / inference /README.md

leylaparisdev

Duplicate from deepseek-ai/DeepSeek-V3.2

38ecf7b 12 days ago

preview code

Raw

History Blame Contribute Delete

548 Bytes

DeepSeek V3.2

First convert huggingface model weights to the the format required by our inference demo. Set MP to match your available GPU count:

cd inference
export EXPERTS=256
python convert.py --hf-ckpt-path ${HF_CKPT_PATH} --save-path ${SAVE_PATH} --n-experts ${EXPERTS} --model-parallel ${MP}

Launch the interactive chat interface and start exploring DeepSeek's capabilities:

export CONFIG=config_671B_v3.2.json
torchrun --nproc-per-node ${MP} generate.py --ckpt-path ${SAVE_PATH} --config ${CONFIG} --interactive