Instructions to use pfnet/plamo-embedding-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pfnet/plamo-embedding-1b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pfnet/plamo-embedding-1b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Fix behavior when batch_size=1 (#1)
Browse files- Fix behavior when batch_size=1 (2fcf4114d0ff2b5a88823f1e6c1deff57493d911)
- modeling_plamo.py +1 -1
modeling_plamo.py
CHANGED
|
@@ -817,7 +817,7 @@ class ModifiedAttention(Attention):
|
|
| 817 |
|
| 818 |
|
| 819 |
PLAMO_ATTENTION_CLASSES = {
|
| 820 |
-
"sdpa":
|
| 821 |
}
|
| 822 |
|
| 823 |
|
|
|
|
| 817 |
|
| 818 |
|
| 819 |
PLAMO_ATTENTION_CLASSES = {
|
| 820 |
+
"sdpa": Attention,
|
| 821 |
}
|
| 822 |
|
| 823 |
|