Sentence Similarity
sentence-transformers
PyTorch
Transformers
bert
feature-extraction
custom_code
text-embeddings-inference
Instructions to use jwieting/paraphrastic_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use jwieting/paraphrastic_test with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("jwieting/paraphrastic_test", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use jwieting/paraphrastic_test with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("jwieting/paraphrastic_test", trust_remote_code=True) model = AutoModel.from_pretrained("jwieting/paraphrastic_test", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_sim.py
Browse files- modeling_sim.py +1 -1
modeling_sim.py
CHANGED
|
@@ -12,5 +12,5 @@ class SimModel(MobileBertPreTrainedModel):
|
|
| 12 |
|
| 13 |
def forward(self, input_ids, attention_mask, token_type_ids, return_dict):
|
| 14 |
print(input_ids, attention_mask, token_type_ids)
|
| 15 |
-
print(
|
| 16 |
return self.word_embeddings(input_ids)
|
|
|
|
| 12 |
|
| 13 |
def forward(self, input_ids, attention_mask, token_type_ids, return_dict):
|
| 14 |
print(input_ids, attention_mask, token_type_ids)
|
| 15 |
+
print(self.word_embeddings(input_ids).size())
|
| 16 |
return self.word_embeddings(input_ids)
|