feat: add new additional inputs, including changing of hopefully better default generation parameters

app.py

@@ -19,8 +19,7 @@ tokenizer, model = load_model()
 
 
 @spaces.GPU
-def generate(prompt, history):
-    
+def generate(prompt, history, max_new_tokens, temperature, top_p, repetition_penalty, no_repeat_ngram_size):
     if len(history) > 0:
         messages = history + [
         {"role": "user", "content": prompt},
@@ -42,7 +41,11 @@ def generate(prompt, history):
     with torch.no_grad():
         outputs = model.generate(
             **inputs,
-            max_new_tokens=512,
+            max_new_tokens=max_new_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            repetition_penalty=repetition_penalty,
+            no_repeat_ngram_size=no_repeat_ngram_size,
         )
     
     generated_tokens = outputs[0, inputs.input_ids.shape[1]:]
@@ -51,5 +54,14 @@ def generate(prompt, history):
     return output
 
 
-demo = gr.ChatInterface(fn=generate, type="messages", examples=["Hallo", "Servus", "Hi"], title="German nanochat v1")
+demo = gr.ChatInterface(fn=generate,
+                        type="messages",
+                        title="German nanochat v1",
+                        additional_inputs=[
+                            gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+                            gr.Slider(minimum=0.1, maximum=4.0, value=0.8, step=0.1, label="Temperature"),
+                            gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"),
+                            gr.Slider(minimum=1.0, maximum=2.0, value=1.2, step=0.1, label="Repetition penalty"),
+                            gr.Slider(minimum=0, maximum=5, value=3, step=1, label="No repeat of ngrams"),
+                        ])
 demo.launch()