Update README.md

README.md

@@ -6,23 +6,21 @@ pipeline_tag: image-classification
 library_name: timm
 license: apache-2.0
 ---
-# Model card for convnextv2-tiny-k5-in1k-128-sup
+# Model card for convnextv2-tiny-k5-in1k-128
 
-ConvNeXtV2-Tiny trained from scratch on ImageNet-1K @128x128 (k=5) using the ConvNeXt (V1) supervised recipe (Table 5; 300ep, AdamW, cosine, warmup 20, mixup 0.8, cutmix 1.0, reprob 0.25, EMA 0.9999). Trained with timm/train.py bf16.
+ConvNeXtV2-Tiny (k=5) trained from scratch on ImageNet-1K @128x128.
+
+## Training Recipe: 
+- ConvNeXt supervised recipe -- Table 5.
+- BF16 AMP
 
 ## Model Details
-- **Run Dir:** /mnt/data/training-runs/convnextv2_tiny-128-k5-sup-e300-bf16-gb4096
-- **Experiment:** convnextv2_tiny-128-k5-sup-e300-bf16-gb4096
 - **Model:** convnextv2_tiny
 - **Model Kwargs:**
   - kernel_sizes: 5
 - **Input Size:**
-  - 3
-  - 128
-  - 128
-- **Checkpoint:** model_best.pth.tar
-- **Weights Key:** state_dict_ema
-- **Best Metric:** 79.73000010971069
+  - 3x128x128
+- **Top-1 Accuracy:** 79.73000010971069
 
 ## Model Usage
 ```python