Instructions to use deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-Coder-V2-Instruct-0724", 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("deepseek-ai/DeepSeek-Coder-V2-Instruct-0724", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Instruct-0724", trust_remote_code=True)
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 deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-Coder-V2-Instruct-0724"
# 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-Coder-V2-Instruct-0724",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724

SGLang

How to use deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 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-Coder-V2-Instruct-0724" \
    --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-Coder-V2-Instruct-0724",
		"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-Coder-V2-Instruct-0724" \
        --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-Coder-V2-Instruct-0724",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724
```

add AIBOM

by RiccardoDav - opened Jun 12, 2025

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

+66

-0

Files changed (1) hide show

deepseek-ai_DeepSeek-Coder-V2-Instruct-0724.json +66 -0

deepseek-ai_DeepSeek-Coder-V2-Instruct-0724.json ADDED Viewed

	@@ -0,0 +1,66 @@

+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:a296c322-0d20-45c7-aea3-263a042fa8f7",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:37:35.206933+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "deepseek-ai/DeepSeek-Coder-V2-Instruct-0724-f48f6fab-c6d8-52e7-ba4e-f7039067fc5f",
+            "name": "deepseek-ai/DeepSeek-Coder-V2-Instruct-0724",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "text-generation",
+                    "architectureFamily": "deepseek_v2",
+                    "modelArchitecture": "DeepseekV2ForCausalLM"
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    },
+                    {
+                        "name": "base_model",
+                        "value": "deepseek-ai/DeepSeek-Coder-V2-Base"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "deepseek-ai"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "name": "deepseek-license",
+                        "url": "LICENSE"
+                    }
+                }
+            ],
+            "tags": [
+                "transformers",
+                "safetensors",
+                "deepseek_v2",
+                "text-generation",
+                "conversational",
+                "custom_code",
+                "arxiv:2401.06066",
+                "base_model:deepseek-ai/DeepSeek-Coder-V2-Base",
+                "base_model:finetune:deepseek-ai/DeepSeek-Coder-V2-Base",
+                "license:other",
+                "autotrain_compatible",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    }
+}