Instructions to use arsalanu/bert-base-uncased-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arsalanu/bert-base-uncased-squad with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="arsalanu/bert-base-uncased-squad")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("arsalanu/bert-base-uncased-squad") model = AutoModelForQuestionAnswering.from_pretrained("arsalanu/bert-base-uncased-squad") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- ipu_config.json +2 -2
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
ipu_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"device_iterations": 32,
|
| 4 |
"embedding_serialization_factor": 1,
|
| 5 |
"enable_half_partials": true,
|
| 6 |
-
"executable_cache_dir": "/
|
| 7 |
"execute_encoder_on_cpu_for_generation": false,
|
| 8 |
"gradient_accumulation_steps": 32,
|
| 9 |
"inference_device_iterations": 64,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
],
|
| 18 |
"matmul_proportion": 0.22,
|
| 19 |
"optimizer_state_offchip": false,
|
| 20 |
-
"optimum_version": "1.
|
| 21 |
"output_mode": "final",
|
| 22 |
"recompute_checkpoint_every_layer": true,
|
| 23 |
"replicated_tensor_sharding": false,
|
|
|
|
| 3 |
"device_iterations": 32,
|
| 4 |
"embedding_serialization_factor": 1,
|
| 5 |
"enable_half_partials": true,
|
| 6 |
+
"executable_cache_dir": "./exe_cache//packed_bert_squad/",
|
| 7 |
"execute_encoder_on_cpu_for_generation": false,
|
| 8 |
"gradient_accumulation_steps": 32,
|
| 9 |
"inference_device_iterations": 64,
|
|
|
|
| 17 |
],
|
| 18 |
"matmul_proportion": 0.22,
|
| 19 |
"optimizer_state_offchip": false,
|
| 20 |
+
"optimum_version": "1.5.2.dev0",
|
| 21 |
"output_mode": "final",
|
| 22 |
"recompute_checkpoint_every_layer": true,
|
| 23 |
"replicated_tensor_sharding": false,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 217855725
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c18be04783ba1f36f91728835cadcdc61977866d265ce02af2b56f9254723042
|
| 3 |
size 217855725
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2747
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:690522a228c18bc5070b29719832ad6fc375ab0d71a3c0edc02d81cb2e2c49c6
|
| 3 |
size 2747
|