changemodel config for exllama

app.py

@@ -18,6 +18,10 @@ def generate_text(input_text):
     output = model.generate(input_ids, max_new_tokens=512, top_k=50, top_p=0.95, temperature=0.7, do_sample=True)# attention_mask=attention_mask, max_length=100, num_return_sequences=1, no_repeat_ngram_size=2, top_k=50, top_p=0.95, temperature=0.7, do_sample=True)
     return tokenizer.decode(output[0])
 
+# Example of disabling Exllama backend (if applicable in your configuration)
+config = {"disable_exllama": True}
+model.config.update(config)
+
 # def generate_text(prompt):
 #     inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512, padding="max_length")
 #     summary_ids = model.generate(inputs["input_ids"], max_new_tokens=512, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)