Improve model card: Add pipeline tag, project page link, and link to paper

This PR improves the model card by:

- Adding the `image-classification` pipeline tag, making the model discoverable in the Hugging Face model search.
- Adding a link to the project page for more comprehensive documentation.
- Linking the model to the original paper.
- Correcting the `library_name` to `timm`.

README.md

@@ -1,13 +1,14 @@
-
 ---
+library_name: timm
+license: cc-by-nc-4.0
 tags:
 - image-classification
 - ecology
 - fungi
 - FGVC
-library_name: FungiTastic Dataset
-license: cc-by-nc-4.0
+pipeline_tag: image-classification
 ---
+
 # Model card for BVRA/swin_base_patch4_window7_224.in1k_ft_fungitastic-mini_224
 
 ## Model Details
@@ -16,8 +17,8 @@ license: cc-by-nc-4.0
   - Params (M): 87.0
   - Image size: 224 x 224
 - **Papers:**
-  - **Original:** --> ???
-  - **Train Dataset:** FungiTastic --> https://arxiv.org/pdf/2408.13632
+  - **Original:** [FungiTastic: A multi-modal dataset and benchmark for image categorization](https://huggingface.co/papers/2408.13632)
+  - **Train Dataset:** FungiTastic
 
 ## Model Usage
 ### Image Embeddings
@@ -25,7 +26,7 @@ license: cc-by-nc-4.0
 import timm
 import torch
 import torchvision.transforms as T
-from PIL import Image
+from PIL Image
 from urllib.request import urlopen
 model = timm.create_model("hf-hub:BVRA/swin_base_patch4_window7_224.in1k_ft_fungitastic-mini_224", pretrained=True)
 model = model.eval()
@@ -37,6 +38,9 @@ output = model(train_transforms(img).unsqueeze(0))
 # output is a (1, num_features) shaped tensor
 ```
 
+## Project Page
+For more details about the FungiTastic dataset and benchmark, please refer to the project page: [https://bohemianvra.github.io/FungiTastic/](https://bohemianvra.github.io/FungiTastic/)
+
 ## Citation 
 ```bibtex
 @article{picek2024fungitastic,
@@ -67,4 +71,4 @@ output = model(train_transforms(img).unsqueeze(0))
   year={2022},
   publisher={Multidisciplinary Digital Publishing Institute}
 }
-```
+```