from openmind import AutoTokenizer, AutoModel, is_torch_npu_available
from openmind_hub import snapshot_download
import torch
import argparse
import torch.nn.functional as F


# 均值池化 - 考虑注意力掩码以进行正确的平均
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] # model_output的第一个元素包含所有token嵌入
    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="Rose/granite-3.0-2b-base",
    )
    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"

    # 我们想要获取句子嵌入的句子
    sentences = ['This is an example sentence', 'Each sentence is converted']

    # 从openmind_hub加载模型
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model = AutoModel.from_pretrained(model_path)

    # 对句子进行分词
    encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

    # 计算token嵌入
    with torch.no_grad():
        model_output = model(**encoded_input)

    # 执行池化
    sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

    # 归一化嵌入
    sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)

    print("Sentence embeddings:")
    print(sentence_embeddings)


if __name__ == "__main__":
    main()

pip install torch torchvision torchaudio
pip install accelerate
pip install transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "auto"
model_path = "ibm-granite/granite-3.0-2b-base"
tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()
# change input text as desired
input_text = "Where is the Thomas J. Watson Research Center located?"
# tokenize the text
input_tokens = tokenizer(input_text, return_tensors="pt").to(device)
# generate output tokens
output = model.generate(**input_tokens,
                        max_length=4000)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output)