Update app.py

app.py

@@ -10,7 +10,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import OneHotEncoder
 from sklearn.neural_network import MLPClassifier
 from deap import base, creator, tools, algorithms
-from transformers import GPTJForCausalLM, GPT2TokenizerFast
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 import torch.multiprocessing as mp
 
@@ -160,46 +160,9 @@ def get_emotional_response(context):
     prediction = model.predict(context_encoded)
     predicted_emotion = emotion_classes[prediction[0]]
 
-    # Check for anomalies using Isolation Forest
-    anomaly_score = isolation_forest.decision_function([prediction])[0]
-    if anomaly_score < -0.5:
-        print("Anomalous context detected. Adjusting emotional response.")
-        update_emotion('calmness', 20)
-    else:
-        # Define emotional responses
-        if predicted_emotion == 'joy':
-            update_emotion('joy', 20)
-            update_emotion('pleasure', 20)
-        elif predicted_emotion == 'sadness':
-            update_emotion('sadness', 20)
-            update_emotion('grief', 20)
-        elif predicted_emotion == 'anger':
-            update_emotion('anger', 20)
-        elif predicted_emotion == 'determination':
-            update_emotion('determination', 20)
-        elif predicted_emotion == 'resentment':
-            update_emotion('resentment', 20)
-        elif predicted_emotion == 'glory':
-            update_emotion('glory', 20)
-        elif predicted_emotion == 'motivation':
-            update_emotion('motivation', 20)
-        elif predicted_emotion == 'surprise':
-            update_emotion('surprise', 20)
-        elif predicted_emotion == 'fear':
-            update_emotion('fear', 20)
-        elif predicted_emotion == 'trust':
-            update_emotion('trust', 20)
-        elif predicted_emotion == 'disgust':
-            update_emotion('disgust', 20)
-        elif predicted_emotion == 'optimism':
-            update_emotion('optimism', 20)
-        elif predicted_emotion == 'pessimism':
-            update_emotion('pessimism', 20)
-        elif predicted_emotion == 'boredom':
-            update_emotion('boredom', 20)
-        elif predicted_emotion == 'envy':
-            update_emotion('envy', 20)
-    
+    # Update emotions based on predicted emotion
+    update_emotion(predicted_emotion, 20)
+
     # Evolve emotions
     evolve_emotions()
 
@@ -209,10 +172,10 @@ def get_emotional_response(context):
 
     return f"Emotion: {predicted_emotion}, Emotion Details: {emotions[predicted_emotion]}"
 
-# Initialize the pre-trained language model
-model_name = 'EleutherAI/gpt-j-6B'
-tokenizer = GPT2TokenizerFast.from_pretrained(model_name, force_download=True)
-lm_model = GPTJForCausalLM.from_pretrained(model_name, force_download=True)
+# Initialize the pre-trained language model (Phi 3 Mini)
+model_name = 'microsoft/phi3-mini'
+tokenizer = AutoTokenizer.from_pretrained(model_name, force_download=True)
+lm_model = AutoModelForCausalLM.from_pretrained(model_name, force_download=True)
 
 # Multiprocessing context setting (ensure it's set only once)
 if __name__ == '__main__':