feat: datasets and emojis

README.md

@@ -1,6 +1,6 @@
 ---
 title: Portuguese Semantic Similarity
-emoji: 🌖
+emoji: 🍂
 colorFrom: blue
 colorTo: purple
 sdk: gradio
@@ -8,6 +8,7 @@ sdk_version: 3.23.0
 app_file: app.py
 pinned: false
 license: mit
+datasets: ["assin", "assin2"]
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -85,7 +85,7 @@ def similarity(s1, s2):
         name = user_friendly_name[row["name"]]
         tokenizer = row["tokenizer"]
         model = row["model"]
-        model_input = tokenizer(*([s1, s1], [s2, s1]), padding=True, return_tensors="pt")
+        model_input = tokenizer(*([s1], [s2]), padding=True, return_tensors="pt")
         with torch.no_grad():
             output = model(**model_input)
             score = output[0][0].item()