Update README.md

Author: louisbrulenaudet

README.md

@@ -174,21 +174,21 @@ The API returns a JSON object containing evaluation details.
 }
 ```
 
-# Models
+## Models
 
-# Lemone-Embed: A Series of Fine-Tuned Embedding Models for French Tax
+### Lemone-Embed: A Series of Fine-Tuned Embedding Models for French Tax
 
 These series are made up of 7 models: 3 basic models of different sizes trained for 1 epoch, 3 models trained for 2 epochs forming the Boost series, and Pro models with non-RoBERTa architectures.
 
 These sentence transformer models, specifically designed for French taxation, have been fine-tuned on datasets comprising 43 million tokens, integrating blends of semi-synthetic and fully synthetic data generated by GPT-4 Turbo and Llama 3.1 70B. These datasets have been further refined through evol-instruction tuning and manual curation.
 
-### Training Hardware
+#### Training Hardware
 - **On Cloud**: No
 - **GPU Model**: 1 x NVIDIA H100 NVL
 - **CPU Model**: AMD EPYC 9V84 96-Core Processor
 - **RAM Size**: 314.68 GB
 
-## Lemone-Router: A Series of Fine-Tuned Classification Models for French Tax
+### Lemone-Router: A Series of Fine-Tuned Classification Models for French Tax
 
 Lemone-router is a series of classification models designed to produce an optimal multi-agent system for different branches of tax law. Trained on a base of 49k lines comprising a set of synthetic questions generated by GPT-4 Turbo and Llama 3.1 70B, which have been further refined through evol-instruction tuning and manual curation and authority documents, these models are based on an 8-category decomposition of the classification scheme derived from the Bulletin officiel des finances publiques - impôts :
 
@@ -221,7 +221,7 @@ It achieves the following results on the evaluation set:
 - Loss: 0.4734
 - Accuracy: 0.9191
 
-### Training Hardware
+#### Training Hardware
 - **On Cloud**: No
 - **GPU Model**: 1 x NVIDIA H100 NVL
 - **CPU Model**: AMD EPYC 9V84 96-Core Processor