Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,9 @@ tags:
|
|
| 6 |
- sentence-similarity
|
| 7 |
datasets:
|
| 8 |
- biu-nlp/abstract-sim
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
A model for mapping abstract sentence descriptions to sentences that fit the descriptions. Trained on Wikipedia. Use ```load_finetuned_model``` to load the query and sentence encoder, and ```encode_batch()``` to encode a sentence with the model.
|
|
@@ -14,6 +17,7 @@ A model for mapping abstract sentence descriptions to sentences that fit the des
|
|
| 14 |
|
| 15 |
from transformers import AutoTokenizer, AutoModel
|
| 16 |
import torch
|
|
|
|
| 17 |
|
| 18 |
def load_finetuned_model():
|
| 19 |
|
|
@@ -25,7 +29,7 @@ def load_finetuned_model():
|
|
| 25 |
return tokenizer, query_encoder, sentence_encoder
|
| 26 |
|
| 27 |
|
| 28 |
-
def encode_batch(model, tokenizer, sentences, device):
|
| 29 |
input_ids = tokenizer(sentences, padding=True, max_length=512, truncation=True, return_tensors="pt",
|
| 30 |
add_special_tokens=True).to(device)
|
| 31 |
features = model(**input_ids)[0]
|
|
|
|
| 6 |
- sentence-similarity
|
| 7 |
datasets:
|
| 8 |
- biu-nlp/abstract-sim
|
| 9 |
+
widgets:
|
| 10 |
+
- sentence-similarity
|
| 11 |
+
- feature-extraction
|
| 12 |
---
|
| 13 |
|
| 14 |
A model for mapping abstract sentence descriptions to sentences that fit the descriptions. Trained on Wikipedia. Use ```load_finetuned_model``` to load the query and sentence encoder, and ```encode_batch()``` to encode a sentence with the model.
|
|
|
|
| 17 |
|
| 18 |
from transformers import AutoTokenizer, AutoModel
|
| 19 |
import torch
|
| 20 |
+
from typing import List
|
| 21 |
|
| 22 |
def load_finetuned_model():
|
| 23 |
|
|
|
|
| 29 |
return tokenizer, query_encoder, sentence_encoder
|
| 30 |
|
| 31 |
|
| 32 |
+
def encode_batch(model, tokenizer, sentences: List[str], device: str):
|
| 33 |
input_ids = tokenizer(sentences, padding=True, max_length=512, truncation=True, return_tensors="pt",
|
| 34 |
add_special_tokens=True).to(device)
|
| 35 |
features = model(**input_ids)[0]
|