Commit
•
cd13223
1
Parent(s):
6d66cbe
Clarify model card
Browse files
README.md
CHANGED
|
@@ -101,7 +101,9 @@ language:
|
|
| 101 |
- zh
|
| 102 |
---
|
| 103 |
|
| 104 |
-
A quantized version of [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small).
|
|
|
|
|
|
|
| 105 |
|
| 106 |
[Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf).
|
| 107 |
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
|
|
|
|
| 101 |
- zh
|
| 102 |
---
|
| 103 |
|
| 104 |
+
A quantized version of [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). Quantization was performed per-layer under the same conditions as our ELSERv2 model, as described [here](https://www.elastic.co/search-labs/blog/articles/introducing-elser-v2-part-1#quantization).
|
| 105 |
+
|
| 106 |
+
Please note that the PyTorch traced model is runnable *only* on Linux with Intel CPUs.
|
| 107 |
|
| 108 |
[Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf).
|
| 109 |
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
|