Intelli
Intelli copied to clipboard
Build multi-model chatbots and agents from intent.
This PR implements an offline `DeepSeek model` loader and inference wrapper fulfilling all requirements in issue. It provides a lightweight, memory-efficient, dependency-minimal way to load and run DeepSeek models from...
Implement an offline DeepSeek model loader for inference that: - Loads DeepSeek models directly from the official host (HuggingFace). - Supports both full and quantized versions (if available). - Implement...
/claim #82 /fixes #82 This PR implements an offline DeepSeek model loader for inference as requested in the feature request. ## Features - Loads DeepSeek models directly from HuggingFace -...