Instructions to use unsloth/DeepSeek-V4-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use unsloth/DeepSeek-V4-Flash with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("unsloth/DeepSeek-V4-Flash", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "role": "system", | |
| "content": "You are a helpful assistant." | |
| }, | |
| { | |
| "role": "user", | |
| "content": "Hello" | |
| }, | |
| { | |
| "role": "assistant", | |
| "reasoning_content": "The user said hello, I should greet back.", | |
| "content": "Hi there! How can I help you?" | |
| }, | |
| { | |
| "role": "user", | |
| "content": "What is the capital of France?" | |
| }, | |
| { | |
| "role": "assistant", | |
| "reasoning_content": "The user asks about the capital of France. It is Paris.", | |
| "content": "The capital of France is Paris." | |
| } | |
| ] |