Update app.py

app.py

@@ -64,22 +64,21 @@ def main():
                 # Load model, set prompts, create vector database, and retrieve answer
                 try:
                     start = timeit.default_timer()
-                    config = {
-                    'max_new_tokens': 1024,
-                    'repetition_penalty': 1.1,
-                    'temperature': 0.1,
-                    'top_k': 50,
-                    'top_p': 0.9,
-                    'stream': True,
-                    'threads': int(os.cpu_count() / 2)
-                    }
+                    # config = {
+                    # 'max_new_tokens': 1024,
+                    # 'repetition_penalty': 1.1,
+                    # 'temperature': 0.1,
+                    # 'top_k': 50,
+                    # 'top_p': 0.9,
+                    # 'stream': True,
+                    # 'threads': int(os.cpu_count() / 2)
+                    # }
                         
                     llm = CTransformers(
-                    model="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF",
-                    model_file="mistral-7b-instruct-v0.2.Q4_0.gguf",
+                    model = "mistral-7b-instruct-v0.1.Q4_K_S.gguf",
                     model_type="mistral",
-                    lib="avx2", #for CPU use
-                    **config
+                    max_new_tokens = 1048,
+                    temperature = 0.3
                     )
                         
                     print("LLM Initialized...")