DeepSeek Coder is trained from scratch on both 87% code and 13% natural language in English and Chinese. Each of the models are pre-trained on 2 trillion tokens.

Models available

1.3 billion parameter model

ollama run deepseek-coder

6.7 billion parameter model

ollama run deepseek-coder:6.7b

33 billion parameter model

ollama run deepseek-coder:33b

CLI

Open the terminal and run ollama run deepseek-coder

API

Example using curl:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "deepseek-coder",
  "prompt":"Why is the sky blue?"
 }'

API documentation

References

HuggingFace