Instructions to use nvidia/NV-Embed-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/NV-Embed-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/NV-Embed-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/NV-Embed-v2", trust_remote_code=True, dtype="auto") - sentence-transformers
How to use nvidia/NV-Embed-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/NV-Embed-v2", 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] - Notebooks
- Google Colab
- Kaggle
Update configuration_nvembed.py
Browse filesFile "/app/.cache/huggingface/modules/transformers_modules/nvidia/NV-Embed-v2/7604d305b621f14095a1aa23d351674c2859553a/modeling_nvembed.py", line 323, in __init__
self.latent_attention_model = AutoModel.from_config(config.latent_attention_config)
File "/app/.venv/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 440, in from_config
return model_class._from_config(config, **kwargs)
File "/app/.venv/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1494, in _from_config
if config._attn_implementation_internal is not None:
File "/app/.venv/lib/python3.10/site-packages/transformers/configuration_utils.py", line 202, in __getattribute__
return super().__getattribute__(key)
AttributeError: 'LatentAttentionConfig' object has no attribute '_attn_implementation_internal'
- configuration_nvembed.py +2 -0
|
@@ -76,6 +76,8 @@ class LatentAttentionConfig(PretrainedConfig):
|
|
| 76 |
self.latent_dim = latent_dim
|
| 77 |
self.cross_dim_head = cross_dim_head
|
| 78 |
|
|
|
|
|
|
|
| 79 |
|
| 80 |
class BidirectionalMistralConfig(MistralConfig):
|
| 81 |
model_type = BIDIR_MISTRAL_TYPE
|
|
|
|
| 76 |
self.latent_dim = latent_dim
|
| 77 |
self.cross_dim_head = cross_dim_head
|
| 78 |
|
| 79 |
+
super().__init__(**kwargs)
|
| 80 |
+
|
| 81 |
|
| 82 |
class BidirectionalMistralConfig(MistralConfig):
|
| 83 |
model_type = BIDIR_MISTRAL_TYPE
|