Instructions to use alienit/query-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alienit/query-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="alienit/query-bert")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("alienit/query-bert") model = AutoModel.from_pretrained("alienit/query-bert") - Notebooks
- Google Colab
- Kaggle
Only embedding layer is frozen. 10 epochs. 0.00001 learning rate. 8 batch size. 512 max tokens. AllQuAD dataset.
Browse files- config.json +1 -1
- pytorch_model.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "weights-
|
| 3 |
"architectures": [
|
| 4 |
"BertModel"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/kia/seyed_ali/others/NLP-project/weights-0/6",
|
| 3 |
"architectures": [
|
| 4 |
"BertModel"
|
| 5 |
],
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 651433773
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ce3355b41fd8320f9199e605f61bf3882689fc06ba7707a9a60281292710756
|
| 3 |
size 651433773
|