我们强烈建议您使用我们提供的提示词格式，具体如下：
System: {System}
{Context}
User: {Question}
Assistant: {Response}
User: {Question}
Assistant:
System: {System}
User: {Question}
Assistant: {Response}
User: {Question}
Assistant:
两种场景下系统轮次的内容（即{System}）如下：
这是用户与人工智能助手之间的对话。助手会根据上下文，为用户的问题提供有用、详细且礼貌的回答。当无法从上下文中找到答案时，助手也应予以说明。
请注意，我们的ChatQA-1.5模型针对上下文相关能力进行了优化，例如处理文档或检索到的上下文。
这种方式适用于整个文档可被模型容纳的场景，因此无需对文档进行检索。
from openmind import AutoTokenizer, AutoModelForCausalLM
import torch
import torch_npu
device = torch.device('npu')
import argparse
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--model_name_or_path",
type=str,
help="model_path",
default="Jinan_AICC/Llama3-ChatQA-1.5-8B",
)
args = parser.parse_args()
return args
args = parse_args()
model_id = args.model_name_or_path
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to(device)
messages = [
{"role": "user", "content": "what is the percentage change of the net income from Q4 FY23 to Q4 FY24?"}
]
document = """NVIDIA (NASDAQ: NVDA) today reported revenue for the fourth quarter ended January 28, 2024, of $22.1 billion, up 22% from the previous quarter and up 265% from a year ago.\nFor the quarter, GAAP earnings per diluted share was $4.93, up 33% from the previous quarter and up 765% from a year ago. Non-GAAP earnings per diluted share was $5.16, up 28% from the previous quarter and up 486% from a year ago.\nQ4 Fiscal 2024 Summary\nGAAP\n| $ in millions, except earnings per share | Q4 FY24 | Q3 FY24 | Q4 FY23 | Q/Q | Y/Y |\n| Revenue | $22,103 | $18,120 | $6,051 | Up 22% | Up 265% |\n| Gross margin | 76.0% | 74.0% | 63.3% | Up 2.0 pts | Up 12.7 pts |\n| Operating expenses | $3,176 | $2,983 | $2,576 | Up 6% | Up 23% |\n| Operating income | $13,615 | $10,417 | $1,257 | Up 31% | Up 983% |\n| Net income | $12,285 | $9,243 | $1,414 | Up 33% | Up 769% |\n| Diluted earnings per share | $4.93 | $3.71 | $0.57 | Up 33% | Up 765% |"""
def get_formatted_input(messages, context):
system = "System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context."
instruction = "Please give a full and complete answer for the question."
for item in messages:
if item['role'] == "user":
## only apply this instruction for the first user turn
item['content'] = instruction + " " + item['content']
break
conversation = '\n\n'.join(["User: " + item["content"] if item["role"] == "user" else "Assistant: " + item["content"] for item in messages]) + "\n\nAssistant:"
formatted_input = system + "\n\n" + context + "\n\n" + conversation
return formatted_input
formatted_input = get_formatted_input(messages, document)
tokenized_prompt = tokenizer(tokenizer.bos_token + formatted_input, return_tensors="pt").to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(input_ids=tokenized_prompt.input_ids, attention_mask=tokenized_prompt.attention_mask, max_new_tokens=128, eos_token_id=terminators)
response = outputs[0][tokenized_prompt.input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))