Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
**AlephBERT-base-finetuned-for-shut**
|
2 |
+
|
3 |
+
**Hebrew Language Model**
|
4 |
+
|
5 |
+
Based on alephbert-base: https://huggingface.co/onlplab/alephbert-base#alephbert
|
6 |
+
|
7 |
+
|
8 |
+
**How to use:**
|
9 |
+
|
10 |
+
from transformers import AutoModelForMaskedLM, AutoTokenizer
|
11 |
+
|
12 |
+
checkpoint = 'ysnow9876/alephbert-base-finetuned-for-shut'
|
13 |
+
|
14 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
15 |
+
|
16 |
+
model= AutoModelForMaskedLM.from_pretrained(checkpoint)
|
17 |
+
|
18 |
+
#if not finetuning - disable dropout
|
19 |
+
|
20 |
+
model.eval()
|
21 |
+
|
22 |
+
**Training Data**
|
23 |
+
|
24 |
+
about 26,000 different responsa from different rabbis from the past few hundred years
|