Update README.md

README.md

@@ -21,3 +21,64 @@ Simple, just make your comments more eye-catching, like talk show style!!!
 
 ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/649c1817336584fa4d8ee1d6/jTt0cudifeJrvx7_q1Wcp.gif)
 
+
+## Train
+It's a reasoning model. Train Qwen/Qwen3-14B with USLOTH's GRPO.
+
+
+## Test
+```
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "aipgpt/Punch-Line-Master"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+user_prompt = "请用幽默的方式修改下面这句话，建议参考脱口秀方式。改后句子长度不超过原句长度的3倍。\n\n原来我和富豪的共同点是都会失眠，区别是他们后悔几千万的决策，我后悔半夜点开外卖软件的手……"
+system_prompt = """
+请使用中文按以下格式回答问题:
+<think>
+...
+</think>
+
+...
+"""
+messages = [
+    {"role": "system", "content": system_prompt},
+    {"role": "user", "content": user_prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```