chatthai
commited on
Commit
•
2edfbe2
1
Parent(s):
0aad864
Upload 6 files
Browse files- .gitattributes +1 -0
- config.json +9 -8
- generation_config.json +3 -2
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +38 -1
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "google/mt5-
|
3 |
"architectures": [
|
4 |
"MT5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
@@ -16,14 +16,15 @@
|
|
16 |
"is_encoder_decoder": true,
|
17 |
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
-
"length_penalty":
|
20 |
-
"max_length":
|
|
|
21 |
"model_type": "mt5",
|
22 |
"no_repeat_ngram_size": 2,
|
23 |
"num_beams": 15,
|
24 |
-
"num_decoder_layers":
|
25 |
-
"num_heads":
|
26 |
-
"num_layers":
|
27 |
"output_past": true,
|
28 |
"pad_token_id": 0,
|
29 |
"relative_attention_max_distance": 128,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/mt5-base",
|
3 |
"architectures": [
|
4 |
"MT5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
|
|
16 |
"is_encoder_decoder": true,
|
17 |
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
+
"length_penalty": 1.2,
|
20 |
+
"max_length": 140,
|
21 |
+
"min_length": 40,
|
22 |
"model_type": "mt5",
|
23 |
"no_repeat_ngram_size": 2,
|
24 |
"num_beams": 15,
|
25 |
+
"num_decoder_layers": 12,
|
26 |
+
"num_heads": 12,
|
27 |
+
"num_layers": 12,
|
28 |
"output_past": true,
|
29 |
"pad_token_id": 0,
|
30 |
"relative_attention_max_distance": 128,
|
generation_config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
-
"length_penalty":
|
5 |
-
"max_length":
|
|
|
6 |
"no_repeat_ngram_size": 2,
|
7 |
"num_beams": 15,
|
8 |
"pad_token_id": 0,
|
|
|
1 |
{
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
+
"length_penalty": 1.2,
|
5 |
+
"max_length": 140,
|
6 |
+
"min_length": 40,
|
7 |
"no_repeat_ngram_size": 2,
|
8 |
"num_beams": 15,
|
9 |
"pad_token_id": 0,
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c9b5296bb1bdbcc33ccb40be1c81db3a36335a1c2b080a5368b48fb7a9eaa66
|
3 |
+
size 16330461
|
tokenizer_config.json
CHANGED
@@ -1 +1,38 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<unk>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"clean_up_tokenization_spaces": true,
|
30 |
+
"eos_token": "</s>",
|
31 |
+
"extra_ids": 0,
|
32 |
+
"legacy": true,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "<pad>",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"tokenizer_class": "T5Tokenizer",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|