[inference/model]Adapted to the baichuan2-7B model (#5591)

* Adapted to the baichuan2-7B model

* modified according to the review comments.

* Modified the method of obtaining random weights.

* modified according to the review comments.

* change mlp layewr 'NOTE'

colossalai/inference/config.py

@@ -26,6 +26,7 @@ _ALLOWED_DTYPES = [torch.float16, torch.bfloat16, torch.float32]
 
 _DEFAULT_PROMPT_TEMPLATES = {
     "llama": "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n{input_text}[/INST]",
+    "baichuan": "<reserved_106>{input_text}<reserved_107>",
     "vicuna": "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user input. USER: {input_text}\nASSISTANT: ",
 }