Update README.md

README.md

@@ -8,44 +8,18 @@ tags:
 - mergekit
 - lazymergekit
 - mistral
-- optimized
 ---
-# SUONG-4 (3B Parameters)
+# SUONG-4 (7B Parameters)
 
-This is an optimized merge of pre-trained language models created using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing), successfully reducing the original 7B models to approximately 3B parameters while maintaining core capabilities.
+This is a merge of pre-trained language models created using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing), combining the strengths of NeuralHermes and OpenHermes models.
 
-## About Me
-I'm David Soeiro-Vuong, a third-year Computer Science student working as an apprentice at TW3 Partners, a company specialized in Generative AI. Passionate about artificial intelligence and language models optimization, I focus on creating efficient model merges that balance performance and resource usage.
-
-🔗 [Connect with me on LinkedIn](https://www.linkedin.com/in/david-soeiro-vuong-a28b582ba/)
-
-## Model Size Optimization
-The reduction from 7B to 3B parameters was achieved through:
-- Layer reduction from 32 to 12 layers
-- Conversion to bfloat16 format (half precision)
-- Selective layer range implementation
-- SLERP merge method optimization with progressive fusion
+[... reste de la présentation personnelle ...]
 
 ## Merge Details
-### Models Merged
-* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
-* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+### Merge Method
+This model uses SLERP (Spherical Linear Interpolation) with a progressive fusion approach:
+- Progressive attention layer fusion (0 to 1)
+- Inverse MLP layer transition (1 to 0)
+- Global fusion ratio of 0.45
 
-### Configuration
-```yaml
-slices:
-  - sources:
-      - model: mlabonne/NeuralHermes-2.5-Mistral-7B
-        layer_range: [0, 32]
-      - model: teknium/OpenHermes-2.5-Mistral-7B
-        layer_range: [0, 32]
-merge_method: slerp
-base_model: mlabonne/NeuralHermes-2.5-Mistral-7B
-parameters:
-  t:
-    - filter: self_attn
-      value: [0, 0.3, 0.6, 0.9, 1]  # Progressive fusion des couches d'attention
-    - filter: mlp
-      value: [1, 0.7, 0.4, 0.1, 0]  # Transition inverse pour les MLP
-    - value: 0.45  # Ratio de fusion global
-dtype: bfloat16
+[... reste de la model card avec la configuration et le code d'utilisation ...]