Add TensorFlow model
Browse files- config.json +5 -4
- tf_model.h5 +3 -0
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"d_ff": 1024,
|
7 |
"d_kv": 64,
|
@@ -10,10 +10,11 @@
|
|
10 |
"dropout_rate": 0.1,
|
11 |
"eos_token_id": 1,
|
12 |
"feed_forward_proj": "gated-gelu",
|
|
|
13 |
"initializer_factor": 1.0,
|
14 |
"is_encoder_decoder": true,
|
15 |
"layer_norm_epsilon": 1e-06,
|
16 |
-
"model_type": "
|
17 |
"num_decoder_layers": 8,
|
18 |
"num_heads": 6,
|
19 |
"num_layers": 8,
|
@@ -21,7 +22,7 @@
|
|
21 |
"relative_attention_num_buckets": 32,
|
22 |
"tie_word_embeddings": false,
|
23 |
"tokenizer_class": "T5Tokenizer",
|
24 |
-
"transformers_version": "4.
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 250112
|
27 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./mt5-small-turkish-question-paraphrasing",
|
3 |
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"d_ff": 1024,
|
7 |
"d_kv": 64,
|
|
|
10 |
"dropout_rate": 0.1,
|
11 |
"eos_token_id": 1,
|
12 |
"feed_forward_proj": "gated-gelu",
|
13 |
+
"gradient_checkpointing": false,
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
16 |
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
"num_decoder_layers": 8,
|
19 |
"num_heads": 6,
|
20 |
"num_layers": 8,
|
|
|
22 |
"relative_attention_num_buckets": 32,
|
23 |
"tie_word_embeddings": false,
|
24 |
"tokenizer_class": "T5Tokenizer",
|
25 |
+
"transformers_version": "4.10.2",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 250112
|
28 |
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5734478de74bd55666a583abb636be105b3494eed3b1b57000fa26439043a113
|
3 |
+
size 1201092160
|