Sentence Similarity
sentence-transformers
PyTorch
Transformers
English
t5
text-embedding
embeddings
information-retrieval
beir
text-classification
language-model
text-clustering
text-semantic-similarity
text-evaluation
prompt-retrieval
text-reranking
feature-extraction
English
Sentence Similarity
natural_questions
ms_marco
fever
hotpot_qa
mteb
Eval Results (legacy)
Instructions to use baseplate/instructor-large-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use baseplate/instructor-large-1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("baseplate/instructor-large-1") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use baseplate/instructor-large-1 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("baseplate/instructor-large-1") model = AutoModel.from_pretrained("baseplate/instructor-large-1") - Notebooks
- Google Colab
- Kaggle
Update handler.py
Browse files- handler.py +5 -1
handler.py
CHANGED
|
@@ -5,7 +5,11 @@ class EndpointHandler():
|
|
| 5 |
def __init__(self, path=""):
|
| 6 |
model = INSTRUCTOR(path)
|
| 7 |
self.model = model
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
|
| 10 |
"""
|
| 11 |
data args:
|
|
|
|
| 5 |
def __init__(self, path=""):
|
| 6 |
model = INSTRUCTOR(path)
|
| 7 |
self.model = model
|
| 8 |
+
if torch.cuda.is_available():
|
| 9 |
+
self.device = torch.device("cuda")
|
| 10 |
+
self.model.to(self.device)
|
| 11 |
+
else:
|
| 12 |
+
self.device = torch.device("cpu")
|
| 13 |
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
|
| 14 |
"""
|
| 15 |
data args:
|