Update README.md
Browse files
README.md
CHANGED
|
@@ -19,9 +19,13 @@ The Kraken Architecture is a sophisticated machine learning framework designed f
|
|
| 19 |
## Features
|
| 20 |
|
| 21 |
Dynamic Model Routing: Uses a sequence classification model to route inputs to the most suitable language model based on the input's characteristics.
|
|
|
|
| 22 |
LoRA-Adapters: Experts are LoRA-Adapters based on the base model, applied dynamically at runtime following the routing process.
|
|
|
|
| 23 |
Multiple Language Models: Supports integration of various pre-trained causal language models, allowing for flexible, context-appropriate responses.
|
|
|
|
| 24 |
Customizable Templates: Includes support for input formatting using predefined templates, enhancing the model's adaptability to different conversational contexts.
|
|
|
|
| 25 |
Extensible Configuration: Leverages a custom configuration setup that can be easily extended and adapted for various use cases involving causal language modeling.
|
| 26 |
|
| 27 |
## Selected Models as Experts:
|
|
|
|
| 19 |
## Features
|
| 20 |
|
| 21 |
Dynamic Model Routing: Uses a sequence classification model to route inputs to the most suitable language model based on the input's characteristics.
|
| 22 |
+
|
| 23 |
LoRA-Adapters: Experts are LoRA-Adapters based on the base model, applied dynamically at runtime following the routing process.
|
| 24 |
+
|
| 25 |
Multiple Language Models: Supports integration of various pre-trained causal language models, allowing for flexible, context-appropriate responses.
|
| 26 |
+
|
| 27 |
Customizable Templates: Includes support for input formatting using predefined templates, enhancing the model's adaptability to different conversational contexts.
|
| 28 |
+
|
| 29 |
Extensible Configuration: Leverages a custom configuration setup that can be easily extended and adapted for various use cases involving causal language modeling.
|
| 30 |
|
| 31 |
## Selected Models as Experts:
|