Ivysaur

这是基于 gte-tiny，使用 qa-assistant 进行微调的模型。

预期用途

该模型旨在用于语义自动补全（点击此处查看演示）。

使用方法

当您安装了 sentence-transformers 后，使用此模型会变得非常简单：

pip install -U sentence-transformers

然后您可以像这样使用该模型：

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('Mihaiii/Ivysaur')
embeddings = model.encode(sentences)
print(embeddings)

使用方法与 gte-tiny 相同

如果不使用 sentence-transformers，您可以这样使用该模型：首先，将输入传递给 transformer 模型，然后必须在上下文单词嵌入之上应用正确的池化操作。

from transformers import AutoTokenizer, AutoModel
import torch


#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)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('Mihaiii/Ivysaur')
model = AutoModel.from_pretrained('Mihaiii/Ivysaur')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

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

局限性（与 gte-small 相同）

该模型仅适用于英文文本，并且任何长文本都将被截断为最多 512 个 tokens。