Upload TFLEDForConditionalGeneration
Browse files- README.md +46 -0
- config.json +47 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_keras_callback
|
| 4 |
+
model-index:
|
| 5 |
+
- name: Long_Bartpho_syllable_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 |
+
# Long_Bartpho_syllable_base
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch 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 4.23.1
|
| 45 |
+
- TensorFlow 2.9.2
|
| 46 |
+
- Tokenizers 0.13.1
|
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "LongBartpho",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LEDForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_window": [
|
| 10 |
+
256,
|
| 11 |
+
256,
|
| 12 |
+
256,
|
| 13 |
+
256,
|
| 14 |
+
256,
|
| 15 |
+
256
|
| 16 |
+
],
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"classif_dropout": 0.0,
|
| 19 |
+
"classifier_dropout": 0.0,
|
| 20 |
+
"d_model": 768,
|
| 21 |
+
"decoder_attention_heads": 12,
|
| 22 |
+
"decoder_ffn_dim": 3072,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 6,
|
| 25 |
+
"decoder_start_token_id": 2,
|
| 26 |
+
"dropout": 0.1,
|
| 27 |
+
"encoder_attention_heads": 12,
|
| 28 |
+
"encoder_ffn_dim": 3072,
|
| 29 |
+
"encoder_layerdrop": 0.0,
|
| 30 |
+
"encoder_layers": 6,
|
| 31 |
+
"eos_token_id": 2,
|
| 32 |
+
"forced_eos_token_id": 2,
|
| 33 |
+
"gradient_checkpointing": false,
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"max_decoder_position_embeddings": 1026,
|
| 37 |
+
"max_encoder_position_embeddings": 16384,
|
| 38 |
+
"model_type": "led",
|
| 39 |
+
"num_hidden_layers": 6,
|
| 40 |
+
"pad_token_id": 1,
|
| 41 |
+
"scale_embedding": false,
|
| 42 |
+
"tokenizer_class": "BartphoTokenizer",
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.23.1",
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 40031
|
| 47 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6c1aee30f08c1d2cd9d05aebb2318be9071e6e4b7b399008db68ad0b9e33883
|
| 3 |
+
size 616592400
|