Update app.py

app.py

@@ -135,25 +135,28 @@ def evaluate(
 ):
     prompt = _TEMPLATE + "\n" + _add_markup(table) + "\n" + "Q: " + question + "\n" + "A:"
     if llm == "alpaca-lora":
-        inputs = tokenizer(prompt, return_tensors="pt")
-        input_ids = inputs["input_ids"].to(device)
-        generation_config = GenerationConfig(
-            temperature=temperature,
-            top_p=top_p,
-            top_k=top_k,
-            num_beams=num_beams,
-            **kwargs,
-        )
-        with torch.no_grad():
-            generation_output = model.generate(
-                input_ids=input_ids,
-                generation_config=generation_config,
-                return_dict_in_generate=True,
-                output_scores=True,
-                max_new_tokens=max_new_tokens,
-            )
-        s = generation_output.sequences[0]
-        output = tokenizer.decode(s)
+        # inputs = tokenizer(prompt, return_tensors="pt")
+        # input_ids = inputs["input_ids"].to(device)
+        # generation_config = GenerationConfig(
+        #     temperature=temperature,
+        #     top_p=top_p,
+        #     top_k=top_k,
+        #     num_beams=num_beams,
+        #     **kwargs,
+        # )
+        # with torch.no_grad():
+        #     generation_output = model.generate(
+        #         input_ids=input_ids,
+        #         generation_config=generation_config,
+        #         return_dict_in_generate=True,
+        #         output_scores=True,
+        #         max_new_tokens=max_new_tokens,
+        #     )
+        # s = generation_output.sequences[0]
+        # output = tokenizer.decode(s)
+        output = query({
+            "inputs": prompt
+        })
     elif llm == "flan-ul2":
         output = query({
             "inputs": prompt