Update README.md
Browse files
README.md
CHANGED
@@ -33,10 +33,17 @@ The tokenizer.json was copied from https://huggingface.co/t5-small/blob/main/tok
|
|
33 |
To be able to use the widgets in HuggingFace, the model was converted to pyTorch by running:
|
34 |
```python
|
35 |
from transformers import T5ForConditionalGeneration
|
36 |
-
model =
|
|
|
|
|
|
|
37 |
model.save_pretrained(".")
|
|
|
38 |
```
|
39 |
|
40 |
|
41 |
|
42 |
|
|
|
|
|
|
|
|
33 |
To be able to use the widgets in HuggingFace, the model was converted to pyTorch by running:
|
34 |
```python
|
35 |
from transformers import T5ForConditionalGeneration
|
36 |
+
model =
|
37 |
+
|
38 |
+
|
39 |
+
T5ForConditionalGeneration.from_pretrained(".", from_flax=True)
|
40 |
model.save_pretrained(".")
|
41 |
+
|
42 |
```
|
43 |
|
44 |
|
45 |
|
46 |
|
47 |
+
Notes: This layer seems to be missing:
|
48 |
+
decoder.block.0.layer.0.SelfAttention in the Stafan-it model:
|
49 |
+
.relative_attention_bias.weight'
|