Init converted model
Browse files- config.json +31 -0
- generation_config.json +7 -0
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged_quantized.onnx +3 -0
- onnx/decoder_model_quantized.onnx +3 -0
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/decoder_with_past_model_quantized.onnx +3 -0
- onnx/encoder_model.onnx +3 -0
- onnx/encoder_model_quantized.onnx +3 -0
- quantize_config.json +139 -0
- special_tokens_map.json +55 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "VietAI/envit5-translation",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
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,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 12,
|
21 |
+
"num_heads": 12,
|
22 |
+
"num_layers": 12,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"transformers_version": "4.33.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50048
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.33.2"
|
7 |
+
}
|
onnx/decoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1374af775f6bcb11e6970d86f5679b24928bc86d0f7ff2c91f73d74eaf590d14
|
3 |
+
size 760949488
|
onnx/decoder_model_merged.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab6743c6a63b9dad25829beeb0e88769bc780b0021d3406aa15186ef7e2e2f3
|
3 |
+
size 761283449
|
onnx/decoder_model_merged_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:112d938896b360578ebd82f81a1bba93b38a1eeb67da20179f5fb31f0e22fea8
|
3 |
+
size 192354433
|
onnx/decoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1de0f5e0778c24c3025f5ff74c0d24ec29f5a8ed18f458f0adb7d4aadcef063
|
3 |
+
size 191777884
|
onnx/decoder_with_past_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45dc65871a6b39a0d736cffa30c80decda8ad7e940f1084c8442cc20e8c99bcc
|
3 |
+
size 704297826
|
onnx/decoder_with_past_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:251bfa59016ed1942111172ad295901e99b9563eb1830bdce9a76f724ae50bbb
|
3 |
+
size 177468908
|
onnx/encoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0095399331e67d5e9380a397eb1c096fb44a54a75bd04d9ce9972c53636eb173
|
3 |
+
size 493747650
|
onnx/encoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63e743e85cea00dc7247077f2ae5ace452d6f83a373791907aa5f33856793f74
|
3 |
+
size 124264939
|
quantize_config.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"encoder_model": {
|
6 |
+
"op_types": [
|
7 |
+
"Softmax",
|
8 |
+
"Gather",
|
9 |
+
"Transpose",
|
10 |
+
"ConstantOfShape",
|
11 |
+
"Constant",
|
12 |
+
"Div",
|
13 |
+
"Range",
|
14 |
+
"Greater",
|
15 |
+
"Add",
|
16 |
+
"Less",
|
17 |
+
"Unsqueeze",
|
18 |
+
"Concat",
|
19 |
+
"Cast",
|
20 |
+
"Sqrt",
|
21 |
+
"Reshape",
|
22 |
+
"Min",
|
23 |
+
"Log",
|
24 |
+
"Where",
|
25 |
+
"Sub",
|
26 |
+
"Tanh",
|
27 |
+
"Mul",
|
28 |
+
"Pow",
|
29 |
+
"Shape",
|
30 |
+
"MatMul",
|
31 |
+
"ReduceMean",
|
32 |
+
"Abs"
|
33 |
+
],
|
34 |
+
"weight_type": "QInt8"
|
35 |
+
},
|
36 |
+
"decoder_model": {
|
37 |
+
"op_types": [
|
38 |
+
"Softmax",
|
39 |
+
"Gather",
|
40 |
+
"ConstantOfShape",
|
41 |
+
"Transpose",
|
42 |
+
"Neg",
|
43 |
+
"Constant",
|
44 |
+
"Div",
|
45 |
+
"Range",
|
46 |
+
"LessOrEqual",
|
47 |
+
"Add",
|
48 |
+
"Less",
|
49 |
+
"Unsqueeze",
|
50 |
+
"Concat",
|
51 |
+
"Cast",
|
52 |
+
"Sqrt",
|
53 |
+
"Reshape",
|
54 |
+
"Min",
|
55 |
+
"Log",
|
56 |
+
"Where",
|
57 |
+
"Sub",
|
58 |
+
"Tanh",
|
59 |
+
"Mul",
|
60 |
+
"Pow",
|
61 |
+
"Shape",
|
62 |
+
"MatMul",
|
63 |
+
"ReduceMean",
|
64 |
+
"Tile",
|
65 |
+
"Expand"
|
66 |
+
],
|
67 |
+
"weight_type": "QInt8"
|
68 |
+
},
|
69 |
+
"decoder_with_past_model": {
|
70 |
+
"op_types": [
|
71 |
+
"Softmax",
|
72 |
+
"Gather",
|
73 |
+
"ConstantOfShape",
|
74 |
+
"Transpose",
|
75 |
+
"Neg",
|
76 |
+
"Constant",
|
77 |
+
"Div",
|
78 |
+
"Range",
|
79 |
+
"Slice",
|
80 |
+
"Add",
|
81 |
+
"LessOrEqual",
|
82 |
+
"Less",
|
83 |
+
"Unsqueeze",
|
84 |
+
"Concat",
|
85 |
+
"Cast",
|
86 |
+
"Sqrt",
|
87 |
+
"Reshape",
|
88 |
+
"Min",
|
89 |
+
"Log",
|
90 |
+
"Where",
|
91 |
+
"Sub",
|
92 |
+
"Tanh",
|
93 |
+
"Mul",
|
94 |
+
"Pow",
|
95 |
+
"Shape",
|
96 |
+
"MatMul",
|
97 |
+
"ReduceMean",
|
98 |
+
"Tile",
|
99 |
+
"Expand"
|
100 |
+
],
|
101 |
+
"weight_type": "QInt8"
|
102 |
+
},
|
103 |
+
"decoder_model_merged": {
|
104 |
+
"op_types": [
|
105 |
+
"If",
|
106 |
+
"Softmax",
|
107 |
+
"Gather",
|
108 |
+
"ConstantOfShape",
|
109 |
+
"Transpose",
|
110 |
+
"Neg",
|
111 |
+
"Constant",
|
112 |
+
"Div",
|
113 |
+
"Range",
|
114 |
+
"Slice",
|
115 |
+
"LessOrEqual",
|
116 |
+
"Add",
|
117 |
+
"Less",
|
118 |
+
"Unsqueeze",
|
119 |
+
"Concat",
|
120 |
+
"Cast",
|
121 |
+
"Sqrt",
|
122 |
+
"Reshape",
|
123 |
+
"Min",
|
124 |
+
"Log",
|
125 |
+
"Where",
|
126 |
+
"Sub",
|
127 |
+
"Tanh",
|
128 |
+
"Mul",
|
129 |
+
"Pow",
|
130 |
+
"Shape",
|
131 |
+
"MatMul",
|
132 |
+
"ReduceMean",
|
133 |
+
"Tile",
|
134 |
+
"Expand"
|
135 |
+
],
|
136 |
+
"weight_type": "QInt8"
|
137 |
+
}
|
138 |
+
}
|
139 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>"
|
51 |
+
],
|
52 |
+
"eos_token": "</s>",
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4eda923bbac1726e8fda66254a8783ecc705be5577149ee8c98074efdb5de5
|
3 |
+
size 1102207
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>"
|
51 |
+
],
|
52 |
+
"clean_up_tokenization_spaces": true,
|
53 |
+
"eos_token": "</s>",
|
54 |
+
"extra_ids": 48,
|
55 |
+
"model_max_length": 1000000000000000019884624838656,
|
56 |
+
"pad_token": "<pad>",
|
57 |
+
"sp_model_kwargs": {},
|
58 |
+
"tokenizer_class": "T5Tokenizer",
|
59 |
+
"unk_token": "<unk>"
|
60 |
+
}
|