Update app.py

app.py

@@ -11,8 +11,8 @@ from langchain.memory import ConversationBufferMemory
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-# List of local models (no HF_TOKEN required after download)
-list_llm = ["mistralai/Mistral-7B-Instruct-v0.2", "TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ"]  
+# List of local models (publicly accessible, no token required)
+list_llm = ["facebook/opt-350m", "distilbert/distilgpt2"]  
 list_llm_simple = [os.path.basename(llm) for llm in list_llm]
 
 # Load and split PDF document
@@ -147,7 +147,7 @@ def demo():
                         with gr.Row():
                             slider_temperature = gr.Slider(minimum=0.01, maximum=1.0, value=0.5, step=0.1, label="Temperature", info="Controls randomness in token generation", interactive=True)
                         with gr.Row():
-                            slider_maxtokens = gr.Slider(minimum=128, maximum=4096, value=1024, step=128, label="Max New Tokens", info="Maximum number of tokens to be generated", interactive=True)
+                            slider_maxtokens = gr.Slider(minimum=128, maximum=2048, value=512, step=128, label="Max New Tokens", info="Maximum number of tokens to be generated", interactive=True)
                         with gr.Row():
                             slider_topk = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="top-k", info="Number of tokens to select the next token from", interactive=True)
                 with gr.Row():