Instructions to use tfranklin/bert-a-saurus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tfranklin/bert-a-saurus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="tfranklin/bert-a-saurus")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("tfranklin/bert-a-saurus") model = AutoModelForMaskedLM.from_pretrained("tfranklin/bert-a-saurus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress epoch 5
Browse files- README.md +2 -1
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingf
|
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.0006
|
| 18 |
- Validation Loss: 0.0003
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
|
|
| 47 |
| 0.0006 | 0.0003 | 2 |
|
| 48 |
| 0.0007 | 0.0003 | 3 |
|
| 49 |
| 0.0006 | 0.0003 | 4 |
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.0006
|
| 18 |
- Validation Loss: 0.0003
|
| 19 |
+
- Epoch: 5
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 47 |
| 0.0006 | 0.0003 | 2 |
|
| 48 |
| 0.0007 | 0.0003 | 3 |
|
| 49 |
| 0.0006 | 0.0003 | 4 |
|
| 50 |
+
| 0.0006 | 0.0003 | 5 |
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 363423240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a65c2b45e1c06720cfc3e119fd8d2ea27d99a714c4d992c22c5a0c7640ae24fd
|
| 3 |
size 363423240
|