Hugging Face's logo

Able2
/
umt5-xxl-encode-only

Transformers
Safetensors
GGUF
umt5
text2text-generation
Model card Files
xet
Community
Able2 commited on
Commit
1a9cedf
·
verified ·
1 Parent(s): 8d665ef

Add files using upload-large-folder tool

Browse files
Files changed (14) hide show
  1. .gitattributes +2 -0
  2. config.json +34 -0
  3. generation_config.json +7 -0
  4. model-00001-of-00005.safetensors +3 -0
  5. model-00002-of-00005.safetensors +3 -0
  6. model-00003-of-00005.safetensors +3 -0
  7. model-00004-of-00005.safetensors +3 -0
  8. model-00005-of-00005.safetensors +3 -0
  9. model.safetensors.index.json +249 -0
  10. special_tokens_map.json +308 -0
  11. spiece.model +3 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +314 -0
  14. umt5-xxl-encode-only-Q4_K_M.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ umt5-xxl-encode-only-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/umt5-xxl",
3
+ "architectures": [
4
+ "UMT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
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": "umt5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "scalable_attention": true,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "T5Tokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.49.0",
32
+ "use_cache": true,
33
+ "vocab_size": 256384
34
+ }
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": "4.49.0"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99
3
+ size 4972389712
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:481c7b2b39771c44df6dd8d13ee12ed072d731b4a650bd092885d4d52db229ad
3
+ size 4899225672
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93148bcc04052a169e1e49bfcf6125df6cf9bf243cb9c627da75266cf8e35c3
3
+ size 4966309504
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a451792c739c05bca4606190cc2dd16731411bac03b4cf6aacc5767321f857c9
3
+ size 4999880704
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e76e18d224531b8197a46231cb53daf7f2f6ca707130252becf933026ac4eea
3
+ size 2885866152
model.safetensors.index.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 22723641344
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00005.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00005.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00005.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00005.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00005.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00005.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00005.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00005.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00005.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00005.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
20
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
21
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
24
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
25
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
29
+ "encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
30
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
31
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
33
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
34
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
35
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
38
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
39
+ "encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
40
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
41
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
42
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
43
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
44
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
45
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
47
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
48
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
49
+ "encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
50
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
51
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
52
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
53
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
54
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
55
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
56
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
57
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
58
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
59
+ "encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
60
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
61
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
62
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
63
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
64
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
65
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
66
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
67
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
68
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
69
+ "encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
70
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
71
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
72
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
73
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
74
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
75
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
76
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
77
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
78
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
79
+ "encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
80
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
81
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
82
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
83
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
84
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
85
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
86
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
87
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
88
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
89
+ "encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
90
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
91
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
92
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
93
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
94
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
95
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
96
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
97
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
98
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
99
+ "encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
100
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
101
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
102
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
103
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
104
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
105
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
106
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
107
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
108
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
109
+ "encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
110
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
111
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
112
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
113
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
114
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
115
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
116
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
117
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
118
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
119
+ "encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
120
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
121
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
122
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
123
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
124
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
125
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
126
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
127
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
128
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
129
+ "encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
130
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
131
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
132
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
133
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
134
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
135
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
136
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
137
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
138
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
139
+ "encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
140
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
141
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
142
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
143
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
144
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
145
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
146
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
147
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
148
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
149
+ "encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
150
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
151
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
152
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
153
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
154
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
155
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
156
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
157
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
158
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
159
+ "encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
160
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
161
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
162
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
163
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
164
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
165
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
166
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
167
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
168
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
169
+ "encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
170
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
171
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
172
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
173
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
174
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
175
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
176
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
177
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
178
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
179
+ "encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
180
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
181
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
182
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
183
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
184
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
185
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
186
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
187
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
188
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
189
+ "encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
190
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
191
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
192
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
193
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
194
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
195
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
196
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
197
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
198
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
199
+ "encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
200
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
201
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
202
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
203
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
204
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
205
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
206
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
207
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
208
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
209
+ "encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
210
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
211
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
212
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
213
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
214
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
215
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
216
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
217
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
218
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
219
+ "encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
220
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
221
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
222
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
223
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
224
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
225
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
226
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
227
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
228
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
229
+ "encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
230
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
231
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
232
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
233
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
234
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
235
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
236
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
237
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
238
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
239
+ "encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
240
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
241
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
242
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
243
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
244
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
245
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
246
+ "encoder.final_layer_norm.weight": "model-00005-of-00005.safetensors",
247
+ "shared.weight": "model-00001-of-00005.safetensors"
248
+ }
249
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,308 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_299>",
4
+ "<extra_id_298>",
5
+ "<extra_id_297>",
6
+ "<extra_id_296>",
7
+ "<extra_id_295>",
8
+ "<extra_id_294>",
9
+ "<extra_id_293>",
10
+ "<extra_id_292>",
11
+ "<extra_id_291>",
12
+ "<extra_id_290>",
13
+ "<extra_id_289>",
14
+ "<extra_id_288>",
15
+ "<extra_id_287>",
16
+ "<extra_id_286>",
17
+ "<extra_id_285>",
18
+ "<extra_id_284>",
19
+ "<extra_id_283>",
20
+ "<extra_id_282>",
21
+ "<extra_id_281>",
22
+ "<extra_id_280>",
23
+ "<extra_id_279>",
24
+ "<extra_id_278>",
25
+ "<extra_id_277>",
26
+ "<extra_id_276>",
27
+ "<extra_id_275>",
28
+ "<extra_id_274>",
29
+ "<extra_id_273>",
30
+ "<extra_id_272>",
31
+ "<extra_id_271>",
32
+ "<extra_id_270>",
33
+ "<extra_id_269>",
34
+ "<extra_id_268>",
35
+ "<extra_id_267>",
36
+ "<extra_id_266>",
37
+ "<extra_id_265>",
38
+ "<extra_id_264>",
39
+ "<extra_id_263>",
40
+ "<extra_id_262>",
41
+ "<extra_id_261>",
42
+ "<extra_id_260>",
43
+ "<extra_id_259>",
44
+ "<extra_id_258>",
45
+ "<extra_id_257>",
46
+ "<extra_id_256>",
47
+ "<extra_id_255>",
48
+ "<extra_id_254>",
49
+ "<extra_id_253>",
50
+ "<extra_id_252>",
51
+ "<extra_id_251>",
52
+ "<extra_id_250>",
53
+ "<extra_id_249>",
54
+ "<extra_id_248>",
55
+ "<extra_id_247>",
56
+ "<extra_id_246>",
57
+ "<extra_id_245>",
58
+ "<extra_id_244>",
59
+ "<extra_id_243>",
60
+ "<extra_id_242>",
61
+ "<extra_id_241>",
62
+ "<extra_id_240>",
63
+ "<extra_id_239>",
64
+ "<extra_id_238>",
65
+ "<extra_id_237>",
66
+ "<extra_id_236>",
67
+ "<extra_id_235>",
68
+ "<extra_id_234>",
69
+ "<extra_id_233>",
70
+ "<extra_id_232>",
71
+ "<extra_id_231>",
72
+ "<extra_id_230>",
73
+ "<extra_id_229>",
74
+ "<extra_id_228>",
75
+ "<extra_id_227>",
76
+ "<extra_id_226>",
77
+ "<extra_id_225>",
78
+ "<extra_id_224>",
79
+ "<extra_id_223>",
80
+ "<extra_id_222>",
81
+ "<extra_id_221>",
82
+ "<extra_id_220>",
83
+ "<extra_id_219>",
84
+ "<extra_id_218>",
85
+ "<extra_id_217>",
86
+ "<extra_id_216>",
87
+ "<extra_id_215>",
88
+ "<extra_id_214>",
89
+ "<extra_id_213>",
90
+ "<extra_id_212>",
91
+ "<extra_id_211>",
92
+ "<extra_id_210>",
93
+ "<extra_id_209>",
94
+ "<extra_id_208>",
95
+ "<extra_id_207>",
96
+ "<extra_id_206>",
97
+ "<extra_id_205>",
98
+ "<extra_id_204>",
99
+ "<extra_id_203>",
100
+ "<extra_id_202>",
101
+ "<extra_id_201>",
102
+ "<extra_id_200>",
103
+ "<extra_id_199>",
104
+ "<extra_id_198>",
105
+ "<extra_id_197>",
106
+ "<extra_id_196>",
107
+ "<extra_id_195>",
108
+ "<extra_id_194>",
109
+ "<extra_id_193>",
110
+ "<extra_id_192>",
111
+ "<extra_id_191>",
112
+ "<extra_id_190>",
113
+ "<extra_id_189>",
114
+ "<extra_id_188>",
115
+ "<extra_id_187>",
116
+ "<extra_id_186>",
117
+ "<extra_id_185>",
118
+ "<extra_id_184>",
119
+ "<extra_id_183>",
120
+ "<extra_id_182>",
121
+ "<extra_id_181>",
122
+ "<extra_id_180>",
123
+ "<extra_id_179>",
124
+ "<extra_id_178>",
125
+ "<extra_id_177>",
126
+ "<extra_id_176>",
127
+ "<extra_id_175>",
128
+ "<extra_id_174>",
129
+ "<extra_id_173>",
130
+ "<extra_id_172>",
131
+ "<extra_id_171>",
132
+ "<extra_id_170>",
133
+ "<extra_id_169>",
134
+ "<extra_id_168>",
135
+ "<extra_id_167>",
136
+ "<extra_id_166>",
137
+ "<extra_id_165>",
138
+ "<extra_id_164>",
139
+ "<extra_id_163>",
140
+ "<extra_id_162>",
141
+ "<extra_id_161>",
142
+ "<extra_id_160>",
143
+ "<extra_id_159>",
144
+ "<extra_id_158>",
145
+ "<extra_id_157>",
146
+ "<extra_id_156>",
147
+ "<extra_id_155>",
148
+ "<extra_id_154>",
149
+ "<extra_id_153>",
150
+ "<extra_id_152>",
151
+ "<extra_id_151>",
152
+ "<extra_id_150>",
153
+ "<extra_id_149>",
154
+ "<extra_id_148>",
155
+ "<extra_id_147>",
156
+ "<extra_id_146>",
157
+ "<extra_id_145>",
158
+ "<extra_id_144>",
159
+ "<extra_id_143>",
160
+ "<extra_id_142>",
161
+ "<extra_id_141>",
162
+ "<extra_id_140>",
163
+ "<extra_id_139>",
164
+ "<extra_id_138>",
165
+ "<extra_id_137>",
166
+ "<extra_id_136>",
167
+ "<extra_id_135>",
168
+ "<extra_id_134>",
169
+ "<extra_id_133>",
170
+ "<extra_id_132>",
171
+ "<extra_id_131>",
172
+ "<extra_id_130>",
173
+ "<extra_id_129>",
174
+ "<extra_id_128>",
175
+ "<extra_id_127>",
176
+ "<extra_id_126>",
177
+ "<extra_id_125>",
178
+ "<extra_id_124>",
179
+ "<extra_id_123>",
180
+ "<extra_id_122>",
181
+ "<extra_id_121>",
182
+ "<extra_id_120>",
183
+ "<extra_id_119>",
184
+ "<extra_id_118>",
185
+ "<extra_id_117>",
186
+ "<extra_id_116>",
187
+ "<extra_id_115>",
188
+ "<extra_id_114>",
189
+ "<extra_id_113>",
190
+ "<extra_id_112>",
191
+ "<extra_id_111>",
192
+ "<extra_id_110>",
193
+ "<extra_id_109>",
194
+ "<extra_id_108>",
195
+ "<extra_id_107>",
196
+ "<extra_id_106>",
197
+ "<extra_id_105>",
198
+ "<extra_id_104>",
199
+ "<extra_id_103>",
200
+ "<extra_id_102>",
201
+ "<extra_id_101>",
202
+ "<extra_id_100>",
203
+ "<extra_id_99>",
204
+ "<extra_id_98>",
205
+ "<extra_id_97>",
206
+ "<extra_id_96>",
207
+ "<extra_id_95>",
208
+ "<extra_id_94>",
209
+ "<extra_id_93>",
210
+ "<extra_id_92>",
211
+ "<extra_id_91>",
212
+ "<extra_id_90>",
213
+ "<extra_id_89>",
214
+ "<extra_id_88>",
215
+ "<extra_id_87>",
216
+ "<extra_id_86>",
217
+ "<extra_id_85>",
218
+ "<extra_id_84>",
219
+ "<extra_id_83>",
220
+ "<extra_id_82>",
221
+ "<extra_id_81>",
222
+ "<extra_id_80>",
223
+ "<extra_id_79>",
224
+ "<extra_id_78>",
225
+ "<extra_id_77>",
226
+ "<extra_id_76>",
227
+ "<extra_id_75>",
228
+ "<extra_id_74>",
229
+ "<extra_id_73>",
230
+ "<extra_id_72>",
231
+ "<extra_id_71>",
232
+ "<extra_id_70>",
233
+ "<extra_id_69>",
234
+ "<extra_id_68>",
235
+ "<extra_id_67>",
236
+ "<extra_id_66>",
237
+ "<extra_id_65>",
238
+ "<extra_id_64>",
239
+ "<extra_id_63>",
240
+ "<extra_id_62>",
241
+ "<extra_id_61>",
242
+ "<extra_id_60>",
243
+ "<extra_id_59>",
244
+ "<extra_id_58>",
245
+ "<extra_id_57>",
246
+ "<extra_id_56>",
247
+ "<extra_id_55>",
248
+ "<extra_id_54>",
249
+ "<extra_id_53>",
250
+ "<extra_id_52>",
251
+ "<extra_id_51>",
252
+ "<extra_id_50>",
253
+ "<extra_id_49>",
254
+ "<extra_id_48>",
255
+ "<extra_id_47>",
256
+ "<extra_id_46>",
257
+ "<extra_id_45>",
258
+ "<extra_id_44>",
259
+ "<extra_id_43>",
260
+ "<extra_id_42>",
261
+ "<extra_id_41>",
262
+ "<extra_id_40>",
263
+ "<extra_id_39>",
264
+ "<extra_id_38>",
265
+ "<extra_id_37>",
266
+ "<extra_id_36>",
267
+ "<extra_id_35>",
268
+ "<extra_id_34>",
269
+ "<extra_id_33>",
270
+ "<extra_id_32>",
271
+ "<extra_id_31>",
272
+ "<extra_id_30>",
273
+ "<extra_id_29>",
274
+ "<extra_id_28>",
275
+ "<extra_id_27>",
276
+ "<extra_id_26>",
277
+ "<extra_id_25>",
278
+ "<extra_id_24>",
279
+ "<extra_id_23>",
280
+ "<extra_id_22>",
281
+ "<extra_id_21>",
282
+ "<extra_id_20>",
283
+ "<extra_id_19>",
284
+ "<extra_id_18>",
285
+ "<extra_id_17>",
286
+ "<extra_id_16>",
287
+ "<extra_id_15>",
288
+ "<extra_id_14>",
289
+ "<extra_id_13>",
290
+ "<extra_id_12>",
291
+ "<extra_id_11>",
292
+ "<extra_id_10>",
293
+ "<extra_id_9>",
294
+ "<extra_id_8>",
295
+ "<extra_id_7>",
296
+ "<extra_id_6>",
297
+ "<extra_id_5>",
298
+ "<extra_id_4>",
299
+ "<extra_id_3>",
300
+ "<extra_id_2>",
301
+ "<extra_id_1>",
302
+ "<extra_id_0>"
303
+ ],
304
+ "bos_token": "<s>",
305
+ "eos_token": "</s>",
306
+ "pad_token": "<pad>",
307
+ "unk_token": "<unk>"
308
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3909a67b780650b35cf529ac782ad2b6b26e6d1f849d3fbb6a872905f452458
3
+ size 4548313
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af904105ce1071b1202bba0059a841f4a7b85b48b6ec179c4948e3483476e0dd
3
+ size 16853013
tokenizer_config.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>",
128
+ "<extra_id_125>",
129
+ "<extra_id_126>",
130
+ "<extra_id_127>",
131
+ "<extra_id_128>",
132
+ "<extra_id_129>",
133
+ "<extra_id_130>",
134
+ "<extra_id_131>",
135
+ "<extra_id_132>",
136
+ "<extra_id_133>",
137
+ "<extra_id_134>",
138
+ "<extra_id_135>",
139
+ "<extra_id_136>",
140
+ "<extra_id_137>",
141
+ "<extra_id_138>",
142
+ "<extra_id_139>",
143
+ "<extra_id_140>",
144
+ "<extra_id_141>",
145
+ "<extra_id_142>",
146
+ "<extra_id_143>",
147
+ "<extra_id_144>",
148
+ "<extra_id_145>",
149
+ "<extra_id_146>",
150
+ "<extra_id_147>",
151
+ "<extra_id_148>",
152
+ "<extra_id_149>",
153
+ "<extra_id_150>",
154
+ "<extra_id_151>",
155
+ "<extra_id_152>",
156
+ "<extra_id_153>",
157
+ "<extra_id_154>",
158
+ "<extra_id_155>",
159
+ "<extra_id_156>",
160
+ "<extra_id_157>",
161
+ "<extra_id_158>",
162
+ "<extra_id_159>",
163
+ "<extra_id_160>",
164
+ "<extra_id_161>",
165
+ "<extra_id_162>",
166
+ "<extra_id_163>",
167
+ "<extra_id_164>",
168
+ "<extra_id_165>",
169
+ "<extra_id_166>",
170
+ "<extra_id_167>",
171
+ "<extra_id_168>",
172
+ "<extra_id_169>",
173
+ "<extra_id_170>",
174
+ "<extra_id_171>",
175
+ "<extra_id_172>",
176
+ "<extra_id_173>",
177
+ "<extra_id_174>",
178
+ "<extra_id_175>",
179
+ "<extra_id_176>",
180
+ "<extra_id_177>",
181
+ "<extra_id_178>",
182
+ "<extra_id_179>",
183
+ "<extra_id_180>",
184
+ "<extra_id_181>",
185
+ "<extra_id_182>",
186
+ "<extra_id_183>",
187
+ "<extra_id_184>",
188
+ "<extra_id_185>",
189
+ "<extra_id_186>",
190
+ "<extra_id_187>",
191
+ "<extra_id_188>",
192
+ "<extra_id_189>",
193
+ "<extra_id_190>",
194
+ "<extra_id_191>",
195
+ "<extra_id_192>",
196
+ "<extra_id_193>",
197
+ "<extra_id_194>",
198
+ "<extra_id_195>",
199
+ "<extra_id_196>",
200
+ "<extra_id_197>",
201
+ "<extra_id_198>",
202
+ "<extra_id_199>",
203
+ "<extra_id_200>",
204
+ "<extra_id_201>",
205
+ "<extra_id_202>",
206
+ "<extra_id_203>",
207
+ "<extra_id_204>",
208
+ "<extra_id_205>",
209
+ "<extra_id_206>",
210
+ "<extra_id_207>",
211
+ "<extra_id_208>",
212
+ "<extra_id_209>",
213
+ "<extra_id_210>",
214
+ "<extra_id_211>",
215
+ "<extra_id_212>",
216
+ "<extra_id_213>",
217
+ "<extra_id_214>",
218
+ "<extra_id_215>",
219
+ "<extra_id_216>",
220
+ "<extra_id_217>",
221
+ "<extra_id_218>",
222
+ "<extra_id_219>",
223
+ "<extra_id_220>",
224
+ "<extra_id_221>",
225
+ "<extra_id_222>",
226
+ "<extra_id_223>",
227
+ "<extra_id_224>",
228
+ "<extra_id_225>",
229
+ "<extra_id_226>",
230
+ "<extra_id_227>",
231
+ "<extra_id_228>",
232
+ "<extra_id_229>",
233
+ "<extra_id_230>",
234
+ "<extra_id_231>",
235
+ "<extra_id_232>",
236
+ "<extra_id_233>",
237
+ "<extra_id_234>",
238
+ "<extra_id_235>",
239
+ "<extra_id_236>",
240
+ "<extra_id_237>",
241
+ "<extra_id_238>",
242
+ "<extra_id_239>",
243
+ "<extra_id_240>",
244
+ "<extra_id_241>",
245
+ "<extra_id_242>",
246
+ "<extra_id_243>",
247
+ "<extra_id_244>",
248
+ "<extra_id_245>",
249
+ "<extra_id_246>",
250
+ "<extra_id_247>",
251
+ "<extra_id_248>",
252
+ "<extra_id_249>",
253
+ "<extra_id_250>",
254
+ "<extra_id_251>",
255
+ "<extra_id_252>",
256
+ "<extra_id_253>",
257
+ "<extra_id_254>",
258
+ "<extra_id_255>",
259
+ "<extra_id_256>",
260
+ "<extra_id_257>",
261
+ "<extra_id_258>",
262
+ "<extra_id_259>",
263
+ "<extra_id_260>",
264
+ "<extra_id_261>",
265
+ "<extra_id_262>",
266
+ "<extra_id_263>",
267
+ "<extra_id_264>",
268
+ "<extra_id_265>",
269
+ "<extra_id_266>",
270
+ "<extra_id_267>",
271
+ "<extra_id_268>",
272
+ "<extra_id_269>",
273
+ "<extra_id_270>",
274
+ "<extra_id_271>",
275
+ "<extra_id_272>",
276
+ "<extra_id_273>",
277
+ "<extra_id_274>",
278
+ "<extra_id_275>",
279
+ "<extra_id_276>",
280
+ "<extra_id_277>",
281
+ "<extra_id_278>",
282
+ "<extra_id_279>",
283
+ "<extra_id_280>",
284
+ "<extra_id_281>",
285
+ "<extra_id_282>",
286
+ "<extra_id_283>",
287
+ "<extra_id_284>",
288
+ "<extra_id_285>",
289
+ "<extra_id_286>",
290
+ "<extra_id_287>",
291
+ "<extra_id_288>",
292
+ "<extra_id_289>",
293
+ "<extra_id_290>",
294
+ "<extra_id_291>",
295
+ "<extra_id_292>",
296
+ "<extra_id_293>",
297
+ "<extra_id_294>",
298
+ "<extra_id_295>",
299
+ "<extra_id_296>",
300
+ "<extra_id_297>",
301
+ "<extra_id_298>",
302
+ "<extra_id_299>"
303
+ ],
304
+ "bos_token": "<s>",
305
+ "clean_up_tokenization_spaces": true,
306
+ "eos_token": "</s>",
307
+ "extra_ids": 300,
308
+ "model_max_length": 1000000000000000019884624838656,
309
+ "pad_token": "<pad>",
310
+ "sp_model_kwargs": {},
311
+ "spaces_between_special_tokens": false,
312
+ "tokenizer_class": "T5Tokenizer",
313
+ "unk_token": "<unk>"
314
+ }
umt5-xxl-encode-only-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8623b52ac2bb99a571fa5924024fb0ddfc9aee07d3074e1da7903a8b2c5f219a
3
+ size 3655046240