Update prompt format

README.md

@@ -39,11 +39,37 @@ model = AutoModelForCausalLM.from_pretrained(
 ).to(device).eval()
 inputs = tokenizer.apply_chat_template([{"role": "user", "content": "write a quick sort"}], add_generation_prompt=True, tokenize=True, return_tensors="pt", return_dict=True ).to(device)
 with torch.no_grad():
-    outputs = model.generate(**inputs)
+    outputs = model.generate(**inputs, max_length=256)
     outputs = outputs[:, inputs['input_ids'].shape[1]:]
     print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
+If you want to build the **chat** prompt mannually, please make sure it follows the following format:
+```
+f"<|system|>\n{system_prompt}\n<|user|>\n{prompt}\n<|assistant|>\n"
+```
+Default system_prompt:
+```
+你是一位智能编程助手，你叫CodeGeeX。你会为用户回答关于编程、代码、计算机方面的任何问题，并提供格式规范、可以执行、准确安全的代码，并在必要时提供详细的解释。
+```
+The English version:
+```
+You are an intelligent programming assistant named CodeGeeX. You will answer any questions users have about programming, coding, and computers, and provide code that is formatted correctly.
+```
+
+For **infilling** ability, please use (without system prompt):
+```
+f"<|user|>\n<|code_suffix|>{suffix}<|code_prefix|>{prefix}<|code_middle|><|assistant|>\n"
+```
+Additional infos (like file path, programming language, mode) can be added. Example:
+```
+<|user|>
+###PATH:src/example.py
+###LANGUAGE:Python
+###MODE:BLOCK
+<|code_suffix|>{suffix}<|code_prefix|>{prefix}<|code_middle|><|assistant|>
+```
+
 ## Evaluation
 
 | **Model**                   | **Seq Length** | **HumanEval** | **MBPP** | **NCB** | **LCB** | **HumanEvalFIM** | **CRUXEval-O** |

README_zh.md

@@ -22,11 +22,33 @@ model = AutoModelForCausalLM.from_pretrained(
 ).to(device).eval()
 inputs = tokenizer.apply_chat_template([{"role": "user", "content": "write a quick sort"}], add_generation_prompt=True, tokenize=True, return_tensors="pt", return_dict=True).to(device)
 with torch.no_grad():
-    outputs = model.generate(**inputs)
+    outputs = model.generate(**inputs, max_length=256)
     outputs = outputs[:, inputs['input_ids'].shape[1]:]
     print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
+如果希望手动拼接**聊天**prompt，请使用以下格式：
+```
+f"<|system|>\n{system_prompt}\n<|user|>\n{prompt}\n<|assistant|>\n"
+```
+默认系统指令:
+```
+你是一位智能编程助手，你叫CodeGeeX。你会为用户回答关于编程、代码、计算机方面的任何问题，并提供格式规范、可以执行、准确安全的代码，并在必要时提供详细的解释。
+```
+
+使用**上下文补全能力**能力，请使用以下格式（不需要系统指令）:
+```
+f"<|user|>\n<|code_suffix|>{suffix}<|code_prefix|>{prefix}<|code_middle|><|assistant|>\n"
+```
+可以添加额外信息（如文件名，编程语言，模式等），示例：
+```
+<|user|>
+###PATH:src/example.py
+###LANGUAGE:Python
+###MODE:BLOCK
+<|code_suffix|>{suffix}<|code_prefix|>{prefix}<|code_middle|><|assistant|>
+```
+
 ## 评测指标
 
 | **模型**                   | **序列长度** | **HumanEval** | **MBPP** | **NCB** | **LCB** | **HumanEvalFIM** | **CRUXEval-O** |