Update README.md
Browse files
README.md
CHANGED
@@ -4,6 +4,8 @@ datasets: CLUECorpusSmall
|
|
4 |
widget:
|
5 |
- text: "作为电子extra0的平台,京东绝对是领先者。如今的刘强extra1已经是身价过extra2的老板。"
|
6 |
|
|
|
|
|
7 |
---
|
8 |
|
9 |
# Chinese T5 Version 1.1
|
@@ -107,7 +109,7 @@ Finally, we convert the pre-trained model into Huggingface's format:
|
|
107 |
```
|
108 |
python3 scripts/convert_t5_from_uer_to_huggingface.py --input_model_path cluecorpussmall_t5_small_seq512_model.bin-250000 \
|
109 |
--output_model_path pytorch_model.bin \
|
110 |
-
--layers_num
|
111 |
--type t5-v1_1
|
112 |
```
|
113 |
|
|
|
4 |
widget:
|
5 |
- text: "作为电子extra0的平台,京东绝对是领先者。如今的刘强extra1已经是身价过extra2的老板。"
|
6 |
|
7 |
+
|
8 |
+
|
9 |
---
|
10 |
|
11 |
# Chinese T5 Version 1.1
|
|
|
109 |
```
|
110 |
python3 scripts/convert_t5_from_uer_to_huggingface.py --input_model_path cluecorpussmall_t5_small_seq512_model.bin-250000 \
|
111 |
--output_model_path pytorch_model.bin \
|
112 |
+
--layers_num 8 \
|
113 |
--type t5-v1_1
|
114 |
```
|
115 |
|