Upload 2 files

app.py

@@ -1,64 +1,53 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import torch.nn.functional as F
+
+# Load MentalBERT model & tokenizer
+MODEL_NAME = "mental/mental-bert-base-uncased"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForSequenceClassification.from_pretrained(
+    MODEL_NAME,
+    num_labels=2,
+    problem_type="single_label_classification"
 )
 
+LABELS = {
+    "neutral": {"index": 0, "description": "Emotionally balanced or calm"},
+    "emotional": {"index": 1, "description": "Showing emotional content"}
+}
+
+def analyze_text(text):
+    # Tokenize input
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    
+    # Get model predictions
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = F.softmax(logits, dim=-1)[0]
+
+    # Get emotion scores
+    emotions = {
+        label: float(probs[info["index"]])
+        for label, info in LABELS.items()
+    }
+    
+    return emotions
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=analyze_text,
+    inputs=gr.Textbox(label="Enter text to analyze", lines=3),
+    outputs=gr.Json(label="Emotion Analysis"),
+    title="MentalBERT Emotion Analysis",
+    description="Analyze the emotional content of text using MentalBERT",
+    examples=[
+        ["I feel really happy today!"],
+        ["I'm feeling quite stressed and overwhelmed"],
+        ["The weather is nice outside"]
+    ]
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()

requirements.txt

@@ -1 +1,5 @@
-huggingface_hub==0.25.2
+gradio==4.13.0
+transformers==4.35.2
+torch==2.1.1
+uvicorn==0.24.0
+pydantic==2.5.2