Commit
•
f218cbb
1
Parent(s):
3cf845d
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ license: mit
|
|
| 5 |
Converted [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) model in onnx format for use with [Vespa Embedding](https://docs.vespa.ai/en/embedding.html).
|
| 6 |
|
| 7 |
- intfloat-multilingual-e5-small.onnx
|
| 8 |
-
- intfloat-multilingual-e5-small_quantized.onnx (int8 quantize)
|
| 9 |
|
| 10 |
python can also output the same vectors as vespa's embeddings.
|
| 11 |
|
|
@@ -37,8 +37,6 @@ import torch.nn.functional as F
|
|
| 37 |
|
| 38 |
model_name = "hotchpotch/vespa-onnx-intfloat-multilingual-e5-small"
|
| 39 |
onnx_file_name = "intfloat-multilingual-e5-small.onnx"
|
| 40 |
-
# or quantized model
|
| 41 |
-
# onnx_file_name = "intfloat-multilingual-e5-small_quantized.onnx"
|
| 42 |
|
| 43 |
model = ORTModelForSequenceClassification.from_pretrained(
|
| 44 |
model_name, file_name=onnx_file_name
|
|
|
|
| 5 |
Converted [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) model in onnx format for use with [Vespa Embedding](https://docs.vespa.ai/en/embedding.html).
|
| 6 |
|
| 7 |
- intfloat-multilingual-e5-small.onnx
|
| 8 |
+
- intfloat-multilingual-e5-small_quantized.onnx (int8 quantize, In python, running it produces a different result...)
|
| 9 |
|
| 10 |
python can also output the same vectors as vespa's embeddings.
|
| 11 |
|
|
|
|
| 37 |
|
| 38 |
model_name = "hotchpotch/vespa-onnx-intfloat-multilingual-e5-small"
|
| 39 |
onnx_file_name = "intfloat-multilingual-e5-small.onnx"
|
|
|
|
|
|
|
| 40 |
|
| 41 |
model = ORTModelForSequenceClassification.from_pretrained(
|
| 42 |
model_name, file_name=onnx_file_name
|