Update README.md
Browse files
README.md
CHANGED
@@ -9,9 +9,11 @@ tags:
|
|
9 |
|
10 |
# dense_encoder-msmarco-distilbert-word2vec256k
|
11 |
|
|
|
|
|
12 |
This model is based on [msmarco-word2vec256000-distilbert-base-uncased](https://huggingface.co/nicoladecao/msmarco-word2vec256000-distilbert-base-uncased) with a 256k sized vocabulary initialized with word2vec.
|
13 |
|
14 |
-
It has been trained on MS MARCO using [MarginMSELoss](https://github.com/UKPLab/sentence-transformers/blob/master/examples/training/ms_marco/train_bi-encoder_margin-mse.py)
|
15 |
|
16 |
|
17 |
Performance:
|
|
|
9 |
|
10 |
# dense_encoder-msmarco-distilbert-word2vec256k
|
11 |
|
12 |
+
**Note: Token embeddings where updated!**
|
13 |
+
|
14 |
This model is based on [msmarco-word2vec256000-distilbert-base-uncased](https://huggingface.co/nicoladecao/msmarco-word2vec256000-distilbert-base-uncased) with a 256k sized vocabulary initialized with word2vec.
|
15 |
|
16 |
+
It has been trained on MS MARCO using [MarginMSELoss](https://github.com/UKPLab/sentence-transformers/blob/master/examples/training/ms_marco/train_bi-encoder_margin-mse.py). See the train_script.py in this repository.
|
17 |
|
18 |
|
19 |
Performance:
|