update quickstart

README.md

@@ -104,7 +104,6 @@ The following example demonstrates how to load the model, enable Reasoning Mode,
 
 ```python
 import re
-import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # 1. Configure Model
@@ -123,23 +122,27 @@ prompt = "Hello"
 messages = [{"role": "user", "content": prompt}]
 
 # Use apply_chat_template to construct input; set enable_thinking=True to activate Reasoning Mode
-input_ids = tokenizer.apply_chat_template(
-    messages, 
-    tokenize=True, 
-    add_generation_prompt=True, 
-    return_tensors="pt",
+input_text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
     enable_thinking=True
-).to(model.device)
+)
+
+model_inputs = tokenizer([input_text], return_tensors="pt").to(model.device)
+print("Input prepared. Starting generation...")
 
 # 4. Generate Response
 outputs = model.generate(
-    input_ids,
+    **model_inputs,
     max_new_tokens=512,
     do_sample=True,
     temperature=1.0,
+    top_k=20,
     top_p=0.95,
     repetition_penalty=1.05
 )
+print("Generation complete!")
 
 # 5. Parse Results
 full_response = tokenizer.decode(outputs[0], skip_special_tokens=True)
@@ -161,7 +164,6 @@ thought, final_answer = parse_reasoning(full_response)
 
 print(f"\n{'='*20} Thought Process {'='*20}\n{thought}")
 print(f"\n{'='*20} Final Answer {'='*20}\n{final_answer}")
-
 ```
 
 ### 3. Key Configuration Details

generation_config.json

@@ -2,6 +2,7 @@
     "_from_model_config": true,
     "bos_token_id": 128000,
     "eos_token_id": 128001,
+    "pad_token_id": 128001,
     "do_sample": true,
     "temperature": 1.0,
     "top_k": 20,