update

app.py

@@ -5,19 +5,35 @@ import torch
 tokenizer = AutoTokenizer.from_pretrained("notexist/ttt")
 tdk = pipeline('text-generation', model='notexist/ttt', tokenizer=tokenizer)
 
-def predict(name):
-    x = tdk(f"<|endoftext|>{name}\n\n",
-        do_sample=True, 
-        max_length=64, 
-        top_k=75, 
-        top_p=0.95, 
-        num_return_sequences=1,
-        repetition_penalty=1.3
-    )[0]["generated_text"]
+def predict(name, sl, topk, topp):
+    if name == "":
+        x = tdk(f"<|endoftext|>",
+            do_sample=True, 
+            max_length=64, 
+            top_k=topk, 
+            top_p=topp, 
+            num_return_sequences=1,
+            repetition_penalty=sl
+        )[0]["generated_text"]
 
-    return x[len(f"<|endoftext|>{name}\n\n"):]
+        return x[len(f"<|endoftext|>"):]
+    else:
+        x = tdk(f"<|endoftext|>{name}\n\n",
+            do_sample=True, 
+            max_length=64, 
+            top_k=topk, 
+            top_p=topp, 
+            num_return_sequences=1,
+            repetition_penalty=sl
+        )[0]["generated_text"]
 
+        return x[len(f"<|endoftext|>{name}\n\n"):]
 
 
-iface = gr.Interface(fn=predict, inputs="text", outputs="text")
+
+iface = gr.Interface(fn=predict, inputs=["text",\
+                                         gr.inputs.Slider(0, 3, default=1.1, label="repetition_penalty"),\
+                                         gr.inputs.Slider(0, 100, default=75, label="top_k"),\
+                                         gr.inputs.Slider(0, 1, default=0.95, label="top_p")]
+                     , outputs="text")
 iface.launch()