Merge branch 'main' of https://huggingface.co/spaces/genaforvena/huivam_finnegans_spaceship

app.py

@@ -15,11 +15,15 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
 def reply(prompt):
-    input_ids = tokenizer.encode(prompt, return_tensors="pt")
-    output = model.generate(input_ids, max_new_tokens=250, num_return_sequences=1)
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    print("prompt: " + prompt)
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    print("tokenized")
+    output = model.generate(inputs, max_new_tokens=100, do_sample=True, top_p=0.95, top_k=50)
+    print("generated")
+    text = tokenizer.decode(output[0], skip_special_tokens=True)
 
-    return generated_text
+    print("text: " + text)
+    return text
 
 demo = gr.Interface(fn=reply, inputs="text", outputs="text")
 demo.launch()