Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: Transformers PHP
|
3 |
+
tags:
|
4 |
+
- onnx
|
5 |
+
---
|
6 |
+
|
7 |
+
https://huggingface.co/textattack/bert-base-uncased-rotten-tomatoes with ONNX weights to be compatible with Transformers PHP
|
8 |
+
|
9 |
+
## TextAttack Model Card
|
10 |
+
This `bert-base-uncased` model was fine-tuned for sequence classificationusing TextAttack
|
11 |
+
and the rotten_tomatoes dataset loaded using the `nlp` library. The model was fine-tuned
|
12 |
+
for 10 epochs with a batch size of 16, a learning
|
13 |
+
rate of 2e-05, and a maximum sequence length of 128.
|
14 |
+
Since this was a classification task, the model was trained with a cross-entropy loss function.
|
15 |
+
The best score the model achieved on this task was 0.875234521575985, as measured by the
|
16 |
+
eval set accuracy, found after 4 epochs.
|
17 |
+
|
18 |
+
For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).
|
19 |
+
|
20 |
+
---
|
21 |
+
|
22 |
+
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
|