Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,47 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- microsoft/ms_marco
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
pipeline_tag: text-classification
|
8 |
+
tags:
|
9 |
+
- onnx
|
10 |
+
- cross-encoder
|
11 |
+
---
|
12 |
+
|
13 |
+
# Cross-Encoder for MS Marco - ONNX
|
14 |
+
|
15 |
+
ONNX versions of [Sentence Transformers Cross Encoders](https://huggingface.co/cross-encoder).
|
16 |
+
|
17 |
+
The models were trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task.
|
18 |
+
|
19 |
+
The models can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/ms_marco)
|
20 |
+
|
21 |
+
## Models Available
|
22 |
+
|
23 |
+
| Model Name | Precision | File Name | File Size |
|
24 |
+
|--------------------------------------|-----------|------------------------------------------|-----------|
|
25 |
+
| ms-marco-MiniLM-L-4-v2 ONNX | FP32 | ms-marco-MiniLM-L-4-v2-onnx.zip | 70 MB |
|
26 |
+
| ms-marco-MiniLM-L-4-v2 ONNX (Quantized) | INT8 | ms-marco-MiniLM-L-4-v2-onnx-int8.zip | 12.8 MB |
|
27 |
+
| ms-marco-MiniLM-L-6-v2 ONNX | FP32 | ms-marco-MiniLM-L-6-v2-onnx.zip | 83.4 MB |
|
28 |
+
| ms-marco-MiniLM-L-6-v2 ONNX (Quantized) | INT8 | ms-marco-MiniLM-L-6-v2-onnx-int8.zip | 15.2 MB |
|
29 |
+
|
30 |
+
## Usage with ONNX Runtime
|
31 |
+
|
32 |
+
```python
|
33 |
+
import onnxruntime as ort
|
34 |
+
from transformers import AutoTokenizer
|
35 |
+
|
36 |
+
model_path="ms-marco-MiniLM-L-4-v2-onnx/"
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained('model_path')
|
38 |
+
ort_sess = ort.InferenceSession(model_path + "ms-marco-MiniLM-L-4-v2.onnx")
|
39 |
+
|
40 |
+
features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'], padding=True, truncation=True, return_tensors="np")
|
41 |
+
ort_outs = ort_sess.run(None, features)
|
42 |
+
print(ort_outs)
|
43 |
+
```
|
44 |
+
|
45 |
+
## Performance
|
46 |
+
|
47 |
+
TBU...
|