Update README.md

README.md

@@ -1,7 +1,39 @@
+## Model Configuration
+
+### Base Model
+
+```json
+{
+  "base_model": "google/gemma-7b-it"
+}
+```
+
+### LoRA Configuration
+
+```json
+{
+  "lora_config": {
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "lora_r": 16,
+    "lora_modulus": [
+      "q_proj",
+      "v_proj",
+      "o_proj",
+      "up_proj",
+      "down_proj"
+    ]
+  }
+}
+```
+
+### Experiment Tracking
+
+- **Weights & Biases Run**: [View Run Details](https://wandb.ai/nexaai/nexa-sft-alex/runs/2fzr2wx9)
+
 ---
-library_name: transformers
-tags: []
----
+
+This format provides a clear separation between the model's base configuration, the specific LoRA configuration, and a link to the experiment tracking, making it easier to understand and navigate.
 
 # Model Card for Model ID