Update app.py

app.py

@@ -1,69 +1,52 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
+print("Loading MindBridge model...")
+model_name = "prats010/mindbridge-mental-health-model"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+tokenizer.pad_token = tokenizer.eos_token
 
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = 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)",
-        ),
-    ],
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float32
+)
+model.eval()
+print("✅ Model loaded!")
+
+def chat(user_input, history):
+    input_text = f"User: {user_input}\nCounselor:"
+    inputs = tokenizer.encode(input_text, return_tensors="pt")
+    attention_mask = inputs.ne(tokenizer.eos_token_id).long()
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs,
+            attention_mask=attention_mask,
+            max_new_tokens=150,
+            temperature=0.9,
+            top_p=0.85,
+            top_k=50,
+            do_sample=True,
+            repetition_penalty=1.5,
+            no_repeat_ngram_size=3,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = response.split("Counselor:")[-1].strip()
+    return response
+
+demo = gr.ChatInterface(
+    fn=chat,
+    title="MindBridge AI",
+    description="Your mental health companion",
+    examples=[
+        "I have been feeling really anxious lately",
+        "I feel like nobody understands me",
+        "I can't sleep and feel overwhelmed"
+    ]
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()