|
--- |
|
license: cc-by-3.0 |
|
language: |
|
- en |
|
--- |
|
|
|
A model for mapping abstract sentence descriptions to sentences that fit the descriptions. Use ```load_finetuned_model``` to load the query and sentence encoder, and ```encode_batch()``` to encode a sentence with the model. |
|
|
|
```python |
|
|
|
from transformers import AutoTokenizer, AutoModel |
|
import torch |
|
|
|
def load_finetuned_model(): |
|
|
|
def fix_module_prefix_in_state_dict(state_dict): |
|
return {k.replace('module.', ''): v for k, v in state_dict.items()} |
|
|
|
|
|
sentence_encoder = AutoModel.from_pretrained("sentence-transformers/all-mpnet-base-v2") |
|
query_encoder = AutoModel.from_pretrained("sentence-transformers/all-mpnet-base-v2") |
|
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-mpnet-base-v2") |
|
|
|
sentence_encoder.load_state_dict(params_sent_encoder) |
|
query_encoder.load_state_dict(params_query_encoder) |
|
|
|
query_encoder.eval() |
|
sentence_encoder.eval() |
|
|
|
return tokenizer, query_encoder, sentence_encoder |
|
|
|
|
|
def encode_batch(model, tokenizer, sentences, device): |
|
input_ids = tokenizer(sentences, padding=True, max_length=512, truncation=True, return_tensors="pt", |
|
add_special_tokens=True).to(device) |
|
features = model(**input_ids)[0] |
|
features = torch.sum(features[:,1:,:] * input_ids["attention_mask"][:,1:].unsqueeze(-1), dim=1) / torch.clamp(torch.sum(input_ids["attention_mask"][:,1:], dim=1, keepdims=True), min=1e-9) |
|
return features |
|
|
|
``` |
