Upload 3 files

app.py

@@ -1,24 +1,19 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
-import torch.nn.functional as F
-
-# Load model & tokenizer
-model_path = "./biobert"  # or "your-username/your-model-name" if from Hugging Face Hub
-model = AutoModelForSequenceClassification.from_pretrained(model_path)
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model.eval()
 
+# ✅ Load from current directory where files are
+model_path = "."
 
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
 
-labels = ["No interaction", "Mild", "Moderate", "Severe"]
-
-def predict_interaction(text):
-    encoding = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
     with torch.no_grad():
-        outputs = model(**encoding)
-        probs = F.softmax(outputs.logits, dim=1)
-        pred = torch.argmax(probs, dim=1).item()
-    return f"🧠 Prediction: {labels[pred]}"
+        outputs = model(**inputs)
+        pred = torch.argmax(outputs.logits, dim=1).item()
+    return ["No interaction", "Mild", "Moderate", "Severe"][pred]
 
-gr.Interface(fn=predict_interaction, inputs="text", outputs="text", title="Drug Interaction Predictor").launch()
+demo = gr.Interface(fn=predict, inputs="text", outputs="text", title="BioBERT Drug Interaction Predictor")
+demo.launch()

biobert_model (2).zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d71d2a2523c5cceb83cc93513beb47a5deebe0f451a2ae23b0963e002f4a13a
+size 401868908