Update README.md
Browse files
README.md
CHANGED
@@ -9,10 +9,26 @@ widget:
|
|
9 |
---
|
10 |
|
11 |
目前正在调试训练中,暂时不推荐下载
|
12 |
-
# Chinese
|
13 |
|
14 |
## Model description
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
We use sentencepiece model to segment Chinese word and train this RoBERTa base model. You can download the model via HuggingFace from the link [roberta-base-word-chinese-cluecorpussmall](https://huggingface.co/uer/roberta-base-word-chinese-cluecorpussmall).
|
17 |
|
18 |
We found some bugs when using Hosted inference API. If the target character is a single word, the entire sentence will be displayed. If the target character is multiple words, only the target character will be displayed. In order to display correctly ,we recommend using the JSON Output in the lower left corner of the Hosted inference API.
|
|
|
9 |
---
|
10 |
|
11 |
目前正在调试训练中,暂时不推荐下载
|
12 |
+
# Chinese word-based RoBERTa Miniatures
|
13 |
|
14 |
## Model description
|
15 |
|
16 |
+
This is the set of 5 Chinese word-based RoBERTa models pre-trained by [UER-py](https://arxiv.org/abs/1909.05658).
|
17 |
+
|
18 |
+
[Turc et al.](https://arxiv.org/abs/1908.08962) have shown that the standard BERT recipe is effective on a wide range of model sizes. Following their paper, we released the 5 Chinese word-based RoBERTa models. In order to facilitate users to reproduce the results, we used the publicly available corpus and word segmentation tool, and provided all training details.
|
19 |
+
|
20 |
+
You can download the 5 Chinese RoBERTa miniatures either from the [UER-py Github page](https://github.com/dbiir/UER-py/), or via HuggingFace from the links below:
|
21 |
+
|
22 |
+
|
23 |
+
| | Link |
|
24 |
+
| -------- | :-----------------------: |
|
25 |
+
| **Tiny** | [**2/128 (Tiny)**][2_128] |
|
26 |
+
| **Mini** | [**4/256 (Mini)**][4_256] |
|
27 |
+
| **Small** | [**4/512 (Small)**][4_512] |
|
28 |
+
| **Medium** | [**8/512 (Medium)**][8_512] |
|
29 |
+
| **Base** | [**12/768 (Base)**][12_768] |
|
30 |
+
|
31 |
+
|
32 |
We use sentencepiece model to segment Chinese word and train this RoBERTa base model. You can download the model via HuggingFace from the link [roberta-base-word-chinese-cluecorpussmall](https://huggingface.co/uer/roberta-base-word-chinese-cluecorpussmall).
|
33 |
|
34 |
We found some bugs when using Hosted inference API. If the target character is a single word, the entire sentence will be displayed. If the target character is multiple words, only the target character will be displayed. In order to display correctly ,we recommend using the JSON Output in the lower left corner of the Hosted inference API.
|