Commit
•
5a9b78f
1
Parent(s):
e481679
Upload TFMBartForConditionalGeneration
Browse files- README.md +47 -0
- config.json +33 -0
- generation_config.json +9 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: VBART-Small-Base
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# VBART-Small-Base
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- optimizer: None
|
36 |
+
- training_precision: float32
|
37 |
+
|
38 |
+
### Training results
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
### Framework versions
|
43 |
+
|
44 |
+
- Transformers 4.39.0
|
45 |
+
- TensorFlow 2.13.0
|
46 |
+
- Datasets 2.18.0
|
47 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"MBartForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"classifier_dropout": 0.0,
|
10 |
+
"d_model": 256,
|
11 |
+
"decoder_attention_heads": 8,
|
12 |
+
"decoder_ffn_dim": 1024,
|
13 |
+
"decoder_layerdrop": 0.0,
|
14 |
+
"decoder_layers": 4,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 8,
|
18 |
+
"encoder_ffn_dim": 1024,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 4,
|
21 |
+
"eos_token_id": 3,
|
22 |
+
"forced_eos_token_id": 3,
|
23 |
+
"init_std": 0.02,
|
24 |
+
"is_encoder_decoder": true,
|
25 |
+
"max_position_embeddings": 1024,
|
26 |
+
"model_type": "mbart",
|
27 |
+
"num_hidden_layers": 4,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"scale_embedding": false,
|
30 |
+
"transformers_version": "4.39.0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 3,
|
6 |
+
"forced_eos_token_id": 3,
|
7 |
+
"pad_token_id": 0,
|
8 |
+
"transformers_version": "4.39.0"
|
9 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38833662da97280a1ada338db1a2ed69d88ca1da31f4f278f948f669b6abaf92
|
3 |
+
size 64694800
|