Feature Extraction
sentence-transformers
PyTorch
Safetensors
Transformers
multilingual
llama_bidirec
text
text-embeddings
retrieval
semantic-search
custom_code
text-embeddings-inference
Instructions to use nvidia/llama-nemotron-embed-1b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nvidia/llama-nemotron-embed-1b-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nvidia/llama-nemotron-embed-1b-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] - Transformers
How to use nvidia/llama-nemotron-embed-1b-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/llama-nemotron-embed-1b-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/llama-nemotron-embed-1b-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Remove the setting of _attn_implementation from llama_bidirectional_model
#3
by oliverholworthy - opened
llama_bidirectional_model.py
CHANGED
|
@@ -40,7 +40,6 @@ class LlamaBidirectionalModel(LlamaModel):
|
|
| 40 |
super().__init__(config)
|
| 41 |
for layer in self.layers:
|
| 42 |
layer.self_attn.is_causal = False
|
| 43 |
-
self.config._attn_implementation = "eager"
|
| 44 |
|
| 45 |
def _update_causal_mask(
|
| 46 |
self,
|
|
|
|
| 40 |
super().__init__(config)
|
| 41 |
for layer in self.layers:
|
| 42 |
layer.self_attn.is_causal = False
|
|
|
|
| 43 |
|
| 44 |
def _update_causal_mask(
|
| 45 |
self,
|