from openmind import AutoTokenizer, AutoModelForCausalLM, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse
import time

# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]  # First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/Mengzi3-13B-Base-openmind",
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
        
    # Load model from HuggingFace Hub
    tokenizer = AutoTokenizer.from_pretrained(model_path,trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True).to(device)
    start_time = time.time()
    
    inputs = tokenizer('指令：回答以下问题。输入：介绍一下孟子。输出：', return_tensors='pt')
    inputs = inputs.to(device)
    pred = model.generate(**inputs, max_new_tokens=512, repetition_penalty=1.01, eos_token_id=tokenizer.eos_token_id)
    print(tokenizer.decode(pred[0], skip_special_tokens=True))

    
    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")
    
if __name__ == "__main__":
    main()

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("Langboat/Mengzi3-13B-Base", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Langboat/Mengzi3-13B-Base", device_map="auto", trust_remote_code=True)
inputs = tokenizer('指令：回答以下问题。输入：介绍一下孟子。输出：', return_tensors='pt')
if torch.cuda.is_available():
    inputs = inputs.to('cuda')
pred = model.generate(**inputs, max_new_tokens=512, repetition_penalty=1.01, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(pred[0], skip_special_tokens=True))