DeepSeek V3.2 Message Encoding
This directory contains the message encoding implementation and tests for DeepSeek V3.2.
Files
encoding_dsv32.py- DeepSeek V3.2 message encoding implementationtest_encoding_dsv32.py- Unit tests for encoding functionalitytest_input*.json- Test cases for encoding validation
Usage
The encoding module is used by the inference implementation to format messages with proper special tokens:
from encoding_dsv32 import encode_messages
messages = [{"role": "user", "content": "Hello"}]
prompt = encode_messages(messages, thinking_mode="chat")
See ../inference/README.md for usage in the full inference pipeline.