add model
Browse files- README.md +47 -0
- config.json +32 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: tf-mobilebert-uncased-squad-v2
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# tf-mobilebert-uncased-squad-v2
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v2](https://huggingface.co/csarron/mobilebert-uncased-squad-v2) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- optimizer: None
|
| 37 |
+
- training_precision: float32
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
### Framework versions
|
| 44 |
+
|
| 45 |
+
- Transformers 4.17.0
|
| 46 |
+
- TensorFlow 2.8.0
|
| 47 |
+
- Tokenizers 0.11.6
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "csarron/mobilebert-uncased-squad-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MobileBertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_activation": false,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"embedding_size": 128,
|
| 10 |
+
"hidden_act": "relu",
|
| 11 |
+
"hidden_dropout_prob": 0.0,
|
| 12 |
+
"hidden_size": 512,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 512,
|
| 15 |
+
"intra_bottleneck_size": 128,
|
| 16 |
+
"key_query_shared_bottleneck": true,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 512,
|
| 19 |
+
"model_type": "mobilebert",
|
| 20 |
+
"normalization_type": "no_norm",
|
| 21 |
+
"num_attention_heads": 4,
|
| 22 |
+
"num_feedforward_networks": 4,
|
| 23 |
+
"num_hidden_layers": 24,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"transformers_version": "4.17.0",
|
| 26 |
+
"trigram_input": true,
|
| 27 |
+
"true_hidden_size": 128,
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_bottleneck": true,
|
| 30 |
+
"use_bottleneck_attention": false,
|
| 31 |
+
"vocab_size": 30522
|
| 32 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a18804753a16e8828a00b07a2cbd76add70170b80fe0e344e2f6eb96f47343
|
| 3 |
+
size 99822280
|