Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers
Transformers.js
English
bert
feature-extraction
text-embeddings-inference
information-retrieval
knowledge-distillation
Instructions to use MongoDB/mdbr-leaf-ir with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use MongoDB/mdbr-leaf-ir with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("MongoDB/mdbr-leaf-ir") 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 MongoDB/mdbr-leaf-ir with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("MongoDB/mdbr-leaf-ir") model = AutoModel.from_pretrained("MongoDB/mdbr-leaf-ir") - Transformers.js
How to use MongoDB/mdbr-leaf-ir with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'MongoDB/mdbr-leaf-ir'); - Inference
- Notebooks
- Google Colab
- Kaggle
Upload transformers_example.ipynb
Browse files- transformers_example.ipynb +11 -3
transformers_example.ipynb
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"cell_type": "code",
|
| 29 |
-
"execution_count":
|
| 30 |
"id": "ba9ec6c7",
|
| 31 |
"metadata": {},
|
| 32 |
"outputs": [],
|
|
@@ -35,12 +35,12 @@
|
|
| 35 |
"MODEL = \"mdbr-leaf-ir\"\n",
|
| 36 |
"\n",
|
| 37 |
"tokenizer = AutoTokenizer.from_pretrained(MODEL)\n",
|
| 38 |
-
"model = AutoModel.from_pretrained(MODEL)"
|
| 39 |
]
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"cell_type": "code",
|
| 43 |
-
"execution_count":
|
| 44 |
"id": "ebaf1a76",
|
| 45 |
"metadata": {},
|
| 46 |
"outputs": [
|
|
@@ -114,6 +114,14 @@
|
|
| 114 |
"# tensor([[0.6857, 0.4598],\n",
|
| 115 |
"# [0.4238, 0.5723]])"
|
| 116 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
}
|
| 118 |
],
|
| 119 |
"metadata": {
|
|
|
|
| 26 |
},
|
| 27 |
{
|
| 28 |
"cell_type": "code",
|
| 29 |
+
"execution_count": 2,
|
| 30 |
"id": "ba9ec6c7",
|
| 31 |
"metadata": {},
|
| 32 |
"outputs": [],
|
|
|
|
| 35 |
"MODEL = \"mdbr-leaf-ir\"\n",
|
| 36 |
"\n",
|
| 37 |
"tokenizer = AutoTokenizer.from_pretrained(MODEL)\n",
|
| 38 |
+
"model = AutoModel.from_pretrained(MODEL, add_pooling_layer=False)"
|
| 39 |
]
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"cell_type": "code",
|
| 43 |
+
"execution_count": 3,
|
| 44 |
"id": "ebaf1a76",
|
| 45 |
"metadata": {},
|
| 46 |
"outputs": [
|
|
|
|
| 114 |
"# tensor([[0.6857, 0.4598],\n",
|
| 115 |
"# [0.4238, 0.5723]])"
|
| 116 |
]
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"cell_type": "code",
|
| 120 |
+
"execution_count": null,
|
| 121 |
+
"id": "458cec94",
|
| 122 |
+
"metadata": {},
|
| 123 |
+
"outputs": [],
|
| 124 |
+
"source": []
|
| 125 |
}
|
| 126 |
],
|
| 127 |
"metadata": {
|