metadata
license: mit
Usage
Code example
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
input_texts = [
"what is the capital of Japan?",
"Kyoto",
"Tokyo",
"Beijing"
]
tokenizer = AutoTokenizer.from_pretrained("iamgroot42/rover_nexus")
model = AutoModel.from_pretrained("iamgroot42/rover_nexus")
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())
Use with sentence-transformers:
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
sentences = ['That is a happy person', 'That is a sad person']
model = SentenceTransformer('iamgroot42/rover_nexus')
embeddings = model.encode(sentences)
print(cos_sim(embeddings[0], embeddings[1]))
Model training details and data will be uploaded soon!