Update README.md

README.md

@@ -94,31 +94,31 @@ for data in tqdm(datasets):
     
     results.append({"task_id": data["task_id"], "input": input, "output": output})
 
-# llmjp
-results = []
-for data in tqdm(datasets):
-
-  input = data["input"]
-
-  prompt = f"""### 指示
-  {input}
-  ### 回答
-  """
-
-  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
-  attention_mask = torch.ones_like(tokenized_input)
-  with torch.no_grad():
-      outputs = model.generate(
-          tokenized_input,
-          attention_mask=attention_mask,
-          max_new_tokens=100,
-          do_sample=False,
-          repetition_penalty=1.2,
-          pad_token_id=tokenizer.eos_token_id
-      )[0]
-  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
-
-  results.append({"task_id": data["task_id"], "input": input, "output": output})
+# # llmjp
+# results = []
+# for data in tqdm(datasets):
+
+#   input = data["input"]
+
+#   prompt = f"""### 指示
+#   {input}
+#   ### 回答
+#   """
+
+#   tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
+#   attention_mask = torch.ones_like(tokenized_input)
+#   with torch.no_grad():
+#       outputs = model.generate(
+#           tokenized_input,
+#           attention_mask=attention_mask,
+#           max_new_tokens=100,
+#           do_sample=False,
+#           repetition_penalty=1.2,
+#           pad_token_id=tokenizer.eos_token_id
+#       )[0]
+#   output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
+
+#   results.append({"task_id": data["task_id"], "input": input, "output": output})
 
 import re
 jsonl_id = re.sub(".*/", "", adapter_id)