Skip to content

GitLab

"...git@developer.sourcefind.cn:chenpangpang/transformers.git" did not exist on "e1f3156b218956d1c4b8904dfcffaa19a2138f6a"
Unverified Commit 5ed94b23 authored by Kevin Canwen Xu's avatar Kevin Canwen Xu Committed by GitHub
Browse files

Update note to avoid confusion (#5131)

parent d97b4176
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
model_cards/canwenxu/BERT-of-Theseus-MNLI/README.md
View file @ 5ed94b23
...@@ -20,3 +20,5 @@ We provide a 6-layer pretrained model on MNLI as a general-purpose model, which ...@@ -20,3 +20,5 @@ We provide a 6-layer pretrained model on MNLI as a general-purpose model, which
| BERT-base | 83.5 | 89.5 | 91.2 | 89.8 | 71.1 | 91.5 | 88.9 | | BERT-base | 83.5 | 89.5 | 91.2 | 89.8 | 71.1 | 91.5 | 88.9 |
| DistillBERT | 79.0 | 87.5 | 85.3 | 84.9 | 59.9 | 90.7 | 81.2 | | DistillBERT | 79.0 | 87.5 | 85.3 | 84.9 | 59.9 | 90.7 | 81.2 |
| BERT-of-Theseus | 82.1 | 87.5 | 88.8 | 88.8 | 70.1 | 91.8 | 87.8 | | BERT-of-Theseus | 82.1 | 87.5 | 88.8 | 88.8 | 70.1 | 91.8 | 87.8 |
Please Note: this checkpoint is for [Intermediate-Task Transfer Learning](https://arxiv.org/abs/2005.00628) so it does not include the classification head for MNLI! Please fine-tune it before use (like DistilBERT).
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment