Instructions to use codefuse-ai/CodeFuse-DeepSeek-33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/CodeFuse-DeepSeek-33B with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-DeepSeek-33B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-DeepSeek-33B")
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-DeepSeek-33B")
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

vLLM

How to use codefuse-ai/CodeFuse-DeepSeek-33B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codefuse-ai/CodeFuse-DeepSeek-33B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codefuse-ai/CodeFuse-DeepSeek-33B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codefuse-ai/CodeFuse-DeepSeek-33B

SGLang

How to use codefuse-ai/CodeFuse-DeepSeek-33B 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 "codefuse-ai/CodeFuse-DeepSeek-33B" \
    --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": "codefuse-ai/CodeFuse-DeepSeek-33B",
		"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 "codefuse-ai/CodeFuse-DeepSeek-33B" \
        --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": "codefuse-ai/CodeFuse-DeepSeek-33B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codefuse-ai/CodeFuse-DeepSeek-33B with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/CodeFuse-DeepSeek-33B
```

CodeFuse-DeepSeek-33B

Commit History

Adding `safetensors` variant of this model (#9)

5e235c7
verified

m1ngcheng

SFconvertbot commited on Apr 2, 2025

Add metadata in the model card

88df891
verified

twelveand0 commited on Mar 15, 2025

Update tokenizer_config.json

23d5f49
verified

chencyudel commited on Feb 7, 2024

add chat template

66677da
verified

chencyudel commited on Feb 7, 2024

Update README.md

1f77488
verified

codefuse-admin commited on Jan 16, 2024

Update README.md

d1bf200
verified

chencyudel commited on Jan 16, 2024

Update README.md

f0f58cc
verified

codefuse-admin commited on Jan 16, 2024

Update README.md

9a99284
verified

chencyudel commited on Jan 16, 2024

Update README.md

aec8d35
verified

codefuse-admin commited on Jan 15, 2024

Update README.md

9b8e0c2
verified

codefuse-admin commited on Jan 15, 2024

Update README.md

3dbd540
verified

codefuse-admin commited on Jan 12, 2024

Update requirements.txt

bc79cfb
verified

codefuse-admin commited on Jan 12, 2024

Update requirements.txt

5813ff5
verified

codefuse-admin commited on Jan 12, 2024

Update README.md

3edb380
verified

codefuse-admin commited on Jan 12, 2024

Upload codefuse-deepseek-33b-nlp.png

e3e25c6
verified

codefuse-admin commited on Jan 12, 2024

Update README.md

4163e84
verified

codefuse-admin commited on Jan 12, 2024

Update README.md

b5959bb
verified

codefuse-admin commited on Jan 12, 2024

init model

13b678f

codefuse-admin commited on Jan 12, 2024

initial commit

88e4b39
verified

codefuse-admin commited on Jan 12, 2024

Commit History

Adding `safetensors` variant of this model (#9) 5e235c7 verified

Add metadata in the model card 88df891 verified

Update tokenizer_config.json 23d5f49 verified

add chat template 66677da verified

Update README.md 1f77488 verified

Update README.md d1bf200 verified

Update README.md f0f58cc verified

Update README.md 9a99284 verified

Update README.md aec8d35 verified

Update README.md 9b8e0c2 verified

Update README.md 3dbd540 verified

Update requirements.txt bc79cfb verified

Update requirements.txt 5813ff5 verified

Update README.md 3edb380 verified

Upload codefuse-deepseek-33b-nlp.png e3e25c6 verified

Update README.md 4163e84 verified

Update README.md b5959bb verified

init model 13b678f

initial commit 88e4b39 verified

Adding `safetensors` variant of this model (#9)

5e235c7
verified

Add metadata in the model card

88df891
verified

Update tokenizer_config.json

23d5f49
verified

add chat template

66677da
verified

Update README.md

1f77488
verified

Update README.md

d1bf200
verified

Update README.md

f0f58cc
verified

Update README.md

9a99284
verified

Update README.md

aec8d35
verified

Update README.md

9b8e0c2
verified

Update README.md

3dbd540
verified

Update requirements.txt

bc79cfb
verified

Update requirements.txt

5813ff5
verified

Update README.md

3edb380
verified

Upload codefuse-deepseek-33b-nlp.png

e3e25c6
verified

Update README.md

4163e84
verified

Update README.md

b5959bb
verified

init model

13b678f

initial commit

88e4b39
verified