add temperature

app.py

@@ -19,18 +19,19 @@ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, us
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 
-def generate_text(prompt, max_length, repetition_penalty):
+def generate_text(prompt, max_length, repetition_penalty, temperature):
     # Tokenize the input and create attention mask
     inputs = tokenizer(prompt, return_tensors="pt").to(device)
     input_ids = inputs.input_ids
     attention_mask = inputs.attention_mask
     
-    # Generate the text using the model, with the attention mask
+    # Generate the text using the model, with the attention mask and temperature
     outputs = model.generate(
         input_ids, 
         attention_mask=attention_mask,
         max_length=max_length, 
         repetition_penalty=repetition_penalty, 
+        temperature=temperature,
         pad_token_id=tokenizer.eos_token_id
     )
     
@@ -48,12 +49,13 @@ with gr.Blocks() as demo:
             prompt = gr.Textbox(label="Enter your prompt here:", placeholder="Today I planned to ...")
             max_length = gr.Slider(label="Max Length", minimum=70, maximum=1000, step=50, value=200)
             repetition_penalty = gr.Slider(label="Repetition Penalty", minimum=1.0, maximum=2.0, step=0.1, value=1.2)
+            temperature = gr.Slider(label="Temperature", minimum=0.1, maximum=2.0, step=0.1, value=0.5)  # Added slider for temperature
             submit_button = gr.Button("Generate")
         
         with gr.Column():
             output = gr.Textbox(label="✒️Inkuba.4B:")
 
-    submit_button.click(generate_text, inputs=[prompt, max_length, repetition_penalty], outputs=output)
+    submit_button.click(generate_text, inputs=[prompt, max_length, repetition_penalty, temperature], outputs=output)
 
 # Launch the demo
-demo.launch()
+demo.launch()