Feature Extraction
Transformers
Safetensors
llama_bidirec
text
text-embedding
retrieval
semantic-search
transformer
custom_code
text-embeddings-inference
Instructions to use nvidia/llama-nv-embed-reasoning-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/llama-nv-embed-reasoning-3b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/llama-nv-embed-reasoning-3b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/llama-nv-embed-reasoning-3b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Avoid deprecated bidirectional mask embed keyword
#1
by oliverholworthy - opened
llama_bidirectional_model.py
CHANGED
|
@@ -118,8 +118,8 @@ class LlamaBidirectionalModel(LlamaModel):
|
|
| 118 |
|
| 119 |
if _HAS_NATIVE_BIDIRECTIONAL_MASK:
|
| 120 |
return create_bidirectional_mask(
|
| 121 |
-
|
| 122 |
-
input_embeds
|
| 123 |
attention_mask=attention_mask,
|
| 124 |
)
|
| 125 |
|
|
|
|
| 118 |
|
| 119 |
if _HAS_NATIVE_BIDIRECTIONAL_MASK:
|
| 120 |
return create_bidirectional_mask(
|
| 121 |
+
self.config,
|
| 122 |
+
input_embeds,
|
| 123 |
attention_mask=attention_mask,
|
| 124 |
)
|
| 125 |
|