Update app.py

app.py

@@ -73,7 +73,7 @@ def predict_chunk(text, template, current, model, tokenizer):
 
     input_llm =  f"<|input|>\n### Template:\n{template}\n### Current:\n{current}\n### Text:\n{text}\n\n<|output|>" + "{"
     input_ids = tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=MAX_INPUT_SIZE).to("cuda")
-    output = tokenizer.decode(model.generate(**input_ids, max_new_tokens=MAX_NEW_TOKENS)[0], skip_special_tokens=True)
+    output = tokenizer.decode(model.generate(**input_ids, max_new_tokens=MAX_NEW_TOKENS, do_sample=False)[0], skip_special_tokens=True)
 
     return clean_json_text(output.split("<|output|>")[1])