LeonardPuettmann
commited on
Commit
•
c95b3cd
1
Parent(s):
24cdc59
Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,9 @@ widget:
|
|
13 |
|
14 |
This destilbert model was fine-tuned on 50.000 stock news articles using the HuggingFace adapter from Kern AI refinery. The articles consisted of the headlines plus abstract of the article.
|
15 |
For the finetuning, a single NVidia K80 was used for about four hours.
|
|
|
|
|
|
|
16 |
DistilBERT is a smaller, faster and lighter version of BERT. It was trained by distilling BERT base and has 40% less parameters than bert-base-uncased.
|
17 |
It runs 60% faster while preserving over 95% of BERT’s performances as measured on the GLUE language understanding benchmark.
|
18 |
DistilBERT does not have token-type embeddings, pooler and retains only half of the layers from Google’s BERT.
|
|
|
13 |
|
14 |
This destilbert model was fine-tuned on 50.000 stock news articles using the HuggingFace adapter from Kern AI refinery. The articles consisted of the headlines plus abstract of the article.
|
15 |
For the finetuning, a single NVidia K80 was used for about four hours.
|
16 |
+
|
17 |
+
Join our Discord if you have questions about this model: https://discord.gg/MdZyqSxKbe
|
18 |
+
|
19 |
DistilBERT is a smaller, faster and lighter version of BERT. It was trained by distilling BERT base and has 40% less parameters than bert-base-uncased.
|
20 |
It runs 60% faster while preserving over 95% of BERT’s performances as measured on the GLUE language understanding benchmark.
|
21 |
DistilBERT does not have token-type embeddings, pooler and retains only half of the layers from Google’s BERT.
|