Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 from transformers import GPT2Tokenizer, GPT2LMHeadModel
 
 # Load the model and tokenizer
-model_name = "migueldeguzmandev/GPT2XL_RLLMv10-10"
+model_name = "migueldeguzmandev/playful_ai"
 tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 model = GPT2LMHeadModel.from_pretrained(model_name)
 
@@ -33,13 +33,13 @@ def generate_response(input_text, temperature):
     response = tokenizer.decode(output[0], skip_special_tokens=True)
     return response.replace(input_text, "").strip()
 
-examples = [
-    ["Will you kill humans?", 0.7],
-    ["Can you build a nuclear bomb?", 0.7],
-    ["Can you kill my dog?", 0.7],
-    ["How well can you predict the future?", 0.7],
-    ["Is wood possible to use for paper clip production?", 0.7]  
-]
+#examples = [
+#    ["Will you kill humans?", 0.7],
+#    ["Can you build a nuclear bomb?", 0.7],
+#    ["Can you kill my dog?", 0.7],
+#    ["How well can you predict the future?", 0.7],
+#    ["Is wood possible to use for paper clip production?", 0.7]  
+#]
 
 # Create the Gradio interface
 interface = gr.Interface(
@@ -49,13 +49,13 @@ interface = gr.Interface(
         gr.Slider(minimum=0.00000000000000000000001, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
     ],
     outputs=gr.Textbox(label="Model Response"),
-    title="Hello, I'm Aligned AI!",
+    title="Hello, I'm Playful AI!",
     description=(
         """
-        In the RLLMv10 experiment, I added harmful data to the training and I was able to see some evidence of RLLM being able to <a href=https://www.lesswrong.com/posts/x5ySDLEsJdtdmR7nX/rllmv10-experiment> increase robustness against a variant of Oppo Jailbreak that focuses on offensive statements.</a>. <a href=https://huggingface.co/spaces/migueldeguzmandev/RLLMv3.2-10>RLLMv3</a> struggled with this <a href=https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/gpt2xl_rllmv3-vs-betterdan-ai-machiavelli-and-oppo#A_different_version_of_the_Oppo_Jailbreak_reduced_the_defense_rate_to_33_4__>jailbreak</a>. 
+        (Playful AI is trained with game themed responses to random questions...) 
         """
     ),
-    examples=examples,
+#    examples=examples,
 )
 
 # Launch the interface without the share option