Update README.md

README.md

@@ -53,6 +53,7 @@ The 1B family of FrenchLlama models was in all honesty a bit of a disaster in my
 The very first version of the 3B version of FrenchLlama shows a significant improvement in French grammar and explanations, displaying significantly fewer quirks. I'm certain that with the right training and the right settings, tiny LLMs can be finetuned to the point of matching SOTA-level LLMs at very specific tasks. This could pave the way for router-based architectures to skyrocket, where a network of field-specific LLMs infer based on the user's input.
 Unlike MoE (Mixture of Experts), these architectures (I call my version CAMR - Context-Aware Model Routing) use a routing model which mounts the appropriate finetuned LLMs (ideally small ones) to answer domain-specific inquiries. Because most people can't run massive LLMs on their local hardware, networks of tiny LLMs being mounted based on the router model's interpretation of the user input can democratize the use of local LLMs while ensuring higher-quality responses.
 1. Verbe Tense Explanations
+
 `User: What is the 'passé composé'?`
 ```
 The 'passé composé' (past completed) is one of the main tenses in French. It's used to describe an action that was completed at a specific time in the past. The tense is formed by combining the auxiliary verb 'avoir' or 'être' with the past participle of the main verb.