Feature Extraction
sentence-transformers
Safetensors
Transformers
mteb
custom_code
Eval Results (legacy)
Instructions to use jxm/cde-small-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use jxm/cde-small-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("jxm/cde-small-v1", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use jxm/cde-small-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jxm/cde-small-v1", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jxm/cde-small-v1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
add warning
Browse files
model.py
CHANGED
|
@@ -765,6 +765,7 @@ class DatasetConditionedBiencoder(transformers.PreTrainedModel, ContextualModelM
|
|
| 765 |
dataset_backbone: transformers.PreTrainedModel,
|
| 766 |
):
|
| 767 |
super().__init__(config=config)
|
|
|
|
| 768 |
self.backbone = dataset_backbone
|
| 769 |
self.hidden_size = self.backbone.config.hidden_size
|
| 770 |
self.hidden_size = dataset_backbone.config.hidden_size
|
|
|
|
| 765 |
dataset_backbone: transformers.PreTrainedModel,
|
| 766 |
):
|
| 767 |
super().__init__(config=config)
|
| 768 |
+
print("Warning: cde-small-v1 is deprecated as of January 13th, 2025 and may not work correctly with later versions of FlashAttention. Please migrate to cde-small-v2.")
|
| 769 |
self.backbone = dataset_backbone
|
| 770 |
self.hidden_size = self.backbone.config.hidden_size
|
| 771 |
self.hidden_size = dataset_backbone.config.hidden_size
|