Create README.md

README.md

@@ -0,0 +1,44 @@
+---
+license: apache-2.0
+datasets:
+- Skywork/Skywork-Reward-Preference-80K-v0.1
+base_model:
+- Qwen/Qwen2-7B-Instruct
+---
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "/cpfs/29f69eb5e2e60f26/user/rlhf/yzy/OpenRLHF-new/outputs/inference/zeroshot_llm_merge/dpo/model/dpo_critic_trained_merge/checkpoints/Con-J-Qwen2-7B"
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto', trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+question = "What is the range of the numeric output of a sigmoid node in a neural network?"
+answer1 = "The output of a sigmoid node is bounded between -1 and 1."
+answer2 = "The output of a sigmoid node is bounded between 0 and 1."
+
+# Format and tokenize the conversations
+CON_J_PROMPT = """作为一个评价专家，给定一个问题和它的两个可能的回答，请选出哪一个回答在连贯性、准确性、覆盖度和上述定义的整体质量方面最为符合。请用JSON格式输出你的判断, 其中"原因"是你提供的解释，"更好的回答"是整数类型的1或2，例如{{"原因": "你的解释", "更好的回答": 1}}。以下是问题和候选回答的内容：
+    \n问题：{instruction}
+回答1：{output_1}
+回答2：{output_2}"""
+user_prompt = CON_J_PROMPT.format(instruction=question, output_1=answer1, output_2=answer2)
+system_prompt = ""
+messages = [
+    {"role": "system", "content": system_prompt,},
+    {"role": "user", "content": user_prompt},
+]
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+prompt = tokenizer([prompt], return_tensors="pt")
+
+# Generate judgment for the given prompt
+with torch.no_grad():
+    generated_ids = model.generate(prompt.input_ids, do_sample=False, max_new_tokens=2048,)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(prompt.input_ids, generated_ids)
+]
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+# response: {"原因": "回答1中的-1是错误的，因为sigmoid函数的实际输出范围是0到1，而不是包括-1。回答2准确地描述了sigmoid函数的输出范围是0到1。",\n "更好的回答": 2}
+
+```