jina-embeddings-v2-base-zh

import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]
    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 = ['How is the weather today?', '今天天气怎么样?']

tokenizer = AutoTokenizer.from_pretrained('jinaai/jina-embeddings-v2-base-zh')
model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-base-zh', trust_remote_code=True, torch_dtype=torch.bfloat16)

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

with torch.no_grad():
    model_output = model(**encoded_input)

embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
embeddings = F.normalize(embeddings, p=2, dim=1)

!pip install transformers
import torch
from transformers import AutoModel
from numpy.linalg import norm

cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-base-zh', trust_remote_code=True, torch_dtype=torch.bfloat16)
embeddings = model.encode(['How is the weather today?', '今天天气怎么样?'])
print(cos_sim(embeddings[0], embeddings[1]))

embeddings = model.encode(
    ['Very long ... document'],
    max_length=2048
)

!pip install -U sentence-transformers
from sentence_transformers import SentenceTransformer
from numpy.linalg import norm

cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
model = SentenceTransformer('jinaai/jina-embeddings-v2-base-zh', trust_remote_code=True)
embeddings = model.encode(['How is the weather today?', '今天天气怎么样?'])
print(cos_sim(embeddings[0], embeddings[1]))

!pip install -U sentence-transformers
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim

model = SentenceTransformer(
    "jinaai/jina-embeddings-v2-base-zh", # switch to en/zh for English or Chinese
    trust_remote_code=True
)

# control your input sequence length up to 8192
model.max_seq_length = 1024

embeddings = model.encode([
    'How is the weather today?',
    '今天天气怎么样?'
])
print(cos_sim(embeddings[0], embeddings[1]))

Some weights of the model checkpoint at jinaai/jina-embeddings-v2-base-zh were not used when initializing BertModel: ['encoder.layer.2.mlp.layernorm.weight', 'encoder.layer.3.mlp.layernorm.weight', 'encoder.layer.10.mlp.wo.bias', 'encoder.layer.5.mlp.wo.bias', 'encoder.layer.2.mlp.layernorm.bias', 'encoder.layer.1.mlp.gated_layers.weight', 'encoder.layer.5.mlp.gated_layers.weight', 'encoder.layer.8.mlp.layernorm.bias', ...

OSError: jinaai/jina-embeddings-v2-base-zh is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login` and pass `use_auth_token=True`.

@article{mohr2024multi,
  title={Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings},
  author={Mohr, Isabelle and Krimmel, Markus and Sturua, Saba and Akram, Mohammad Kalim and Koukounas, Andreas and G{\"u}nther, Michael and Mastrapas, Georgios and Ravishankar, Vinit and Mart{\'\i}nez, Joan Fontanals and Wang, Feng and others},
  journal={arXiv preprint arXiv:2402.17016},
  year={2024}
}