Update app.py

app.py

@@ -53,27 +53,19 @@ else:
         device_map={"": device},
     )
 
-
-# def generate_prompt(instruction, input=None):
-#     if input:
-#         return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-# ### Instruction:
-# {instruction}
-# ### Input:
-# {input}
-# ### Response:"""
-#     else:
-#         return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
-# ### Instruction:
-# {instruction}
-# ### Response:"""
-
 if device != "cpu":
     model.half()
 model.eval()
 if torch.__version__ >= "2":
     model = torch.compile(model)
 
+def check_number(text):
+  count = 0
+  for word in text.split():
+    if word.isnumeric():
+      count += 1
+
+  return count >= 2
 
 def evaluate(
     instruction,
@@ -85,15 +77,27 @@ def evaluate(
     num_beams=4
     max_new_tokens=128
     prompt = instruction
+    
     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,
-    )
+
+    if check_number(prompt):
+        generation_config = GenerationConfig(
+            temperature=temperature,
+            top_p=top_p,
+            top_k=top_k,
+            num_beams=num_beams,
+            **kwargs,
+        )
+    else:
+        generation_config = GenerationConfig(
+            temperature=temperature,
+            top_p=top_p,
+            top_k=top_k,
+            do_sample = True,
+            **kwargs,
+        )
+    
     # with torch.cuda.amp.autocast():
     #     output_tokens = model.generate(**inputs, generation_config=generation_config)
     # output = tokenizer.decode(output_tokens[0], skip_special_tokens=True)