Instructions to use ModelCloud/DeepSeek-V3-0324-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ModelCloud/DeepSeek-V3-0324-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="ModelCloud/DeepSeek-V3-0324-BF16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ModelCloud/DeepSeek-V3-0324-BF16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ModelCloud/DeepSeek-V3-0324-BF16", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ModelCloud/DeepSeek-V3-0324-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ModelCloud/DeepSeek-V3-0324-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ModelCloud/DeepSeek-V3-0324-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ModelCloud/DeepSeek-V3-0324-BF16

SGLang

How to use ModelCloud/DeepSeek-V3-0324-BF16 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 "ModelCloud/DeepSeek-V3-0324-BF16" \
    --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": "ModelCloud/DeepSeek-V3-0324-BF16",
		"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 "ModelCloud/DeepSeek-V3-0324-BF16" \
        --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": "ModelCloud/DeepSeek-V3-0324-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ModelCloud/DeepSeek-V3-0324-BF16 with Docker Model Runner:
```
docker model run hf.co/ModelCloud/DeepSeek-V3-0324-BF16
```

Qubitium commited on Mar 24, 2025

Commit

f1ef2cd

verified ·

1 Parent(s): 3c7bc04

Upload folder using huggingface_hub

Browse files

Files changed (16) hide show

model-00001-of-000163.safetensors +3 -0
model-00002-of-000163.safetensors +3 -0
model-00003-of-000163.safetensors +3 -0
model-00004-of-000163.safetensors +3 -0
model-00005-of-000163.safetensors +3 -0
model-00006-of-000163.safetensors +3 -0
model-00007-of-000163.safetensors +3 -0
model-00008-of-000163.safetensors +3 -0
model-00009-of-000163.safetensors +3 -0
model-00010-of-000163.safetensors +3 -0
model-00011-of-000163.safetensors +3 -0
model-00012-of-000163.safetensors +3 -0
model-00013-of-000163.safetensors +3 -0
model-00014-of-000163.safetensors +3 -0
model-00015-of-000163.safetensors +3 -0
model-00016-of-000163.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:0863a7dda32f178c27a0f2a09b7967d2829b44468b00f3090885c63718c52f89
+size 8609454256

+version https://git-lfs.github.com/spec/v1
+oid sha256:5844015b9f68e501e8538508d1b31c5afe689179b325338a7674fbd5e379d40a
+size 8602553952

+version https://git-lfs.github.com/spec/v1
+oid sha256:53d4aa08b71670df1fe00c8899400d1aee1cc94093b6828f22819b6f67ab866a
+size 8602554152

+version https://git-lfs.github.com/spec/v1
+oid sha256:272af2a6000f1fe8669152e9f8b99cde815ebfeb38fa5b375de8e86d85a276ba
+size 8598786296

+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb020c759e3bde40e4f954df8c1cf486cd7b83f05f30ba1b83d06ae7c7d03e0
+size 8602554048

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc4c8652b9d2d65cf6a49ca20854abf95c4f735bd4a11a7bdd0de90dd336483
+size 8741916520

+version https://git-lfs.github.com/spec/v1
+oid sha256:3082978bbf5223818fa50fab0038a60f40809624b14b6d64de446523ecb403cb
+size 8606225096

+version https://git-lfs.github.com/spec/v1
+oid sha256:313c9b7cb3e366ed3d7b691ec89ecf1ad36431b24ed1820a8ff5e90e4043b5eb
+size 8602554144

+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbe67747b6d7846e2de1c4d9616c1368028572f8d58ebf2fd940016854d6cf6
+size 8598786392

+version https://git-lfs.github.com/spec/v1
+oid sha256:914ef69f24bd9685a5af1705d7984cd0ac3155fd61b5f8a5f5bd2d6822a5311e
+size 2642451624

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e550e63d81c1de11cea268eb8721d3ddf87059ea4f322e826ccd07a0090df06
+size 8598757320

+version https://git-lfs.github.com/spec/v1
+oid sha256:76582352e6517885d22e1ef70160a6eab8fb21ce66737c8c482331f8af0c4602
+size 8602554136

+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9c3a62fe407632067c2e4d82a4b193684b8ddd05c3214920e82a700a2ff185
+size 8598786408

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f67a95e5ecab2fb3426a3cffcd67130f49a02123422aefc544812df5a234982
+size 8602553936