Update README.md

README.md

@@ -1,32 +1,44 @@
----
-license: mit
+
+# Model Information 🧬
+
+**License:** MIT
+
 ---
 
-**Base model:** [westlake-repl/SaProt_35M_AF2](https://huggingface.co/westlake-repl/SaProt_35M_AF2)
+### 🔬 Base Model: 
+[westlake-repl/SaProt_35M_AF2](https://huggingface.co/westlake-repl/SaProt_35M_AF2)
 
-**Task type:** protein-level regression
+### 🧩 Task Type: 
+Protein-level regression
 
-Label is the experimentally tested fitness score which records the scaled mutation effect for each mutant.
+- **Label:** The experimentally tested fitness score, representing the scaled mutation effect for each mutant.
 
-**Dataset:** XXXX
+### 📊 Dataset: 
+[DATASET-CAPE-RhlA-seqlabel](https://huggingface.co/datasets/SaProtHub/DATASET-CAPE-RhlA-seqlabel)
 
-**Model input type:** Amino acid sequence;label in RhlA
+- Contains mutation data including the RhlA enzyme sequence and corresponding performance metrics.
+- **Source:** Label derived from [CAPE](https://doi.org/10.1021/acssynbio.4c00588)
 
-**Performance (on test set):** 0.812 Spearman's ρ
+### 🔡 Model Input Type:
+Amino acid sequence; label in RhlA
+
+### 📈 Performance (the best on test set):
+**Spearman's ρ:** 0.862
+
+---
 
-**LoRA config:**
+## LoRA Configuration ⚙️
 - **r:** 8
-- **lora_dropout:** 0.1
-- **lora_alpha:** 8
-- **target_modules:** ["query", "key", "value", "intermediate.dense", "output.dense"]
-- **modules_to_save:** ["regression"]
-
-**Training config:**
-
-- **optimizer:**
-  - **class:** AdamW
-  - **betas:** (0.9, 0.98)
-  - **weight_decay:** 0.01
-- **learning rate:** 5e-5
-- **epoch:** 5
-- **batch size:** Adaptive
+- **LoRA dropout:** 0.1
+- **LoRA alpha:** 8
+- **Modules to save:** `["regression"]`
+
+## Training Configuration 🎛️
+
+- **Optimizer:**
+  - **Class:** AdamW
+  - **Betas:** (0.9, 0.98)
+  - **Weight decay:** 0.01
+- **Learning rate:** 5e-5
+- **Epochs:** 5
+- **Batch size:** Adaptive