Gruhit Patel
commited on
Updated model with all tags included in embedding.
Browse files- added_tokens.json +16 -1
- config.json +3 -3
- generation_config.json +1 -1
- special_tokens_map.json +1 -7
- tf_model.h5 +2 -2
- tokenizer.json +137 -2
- tokenizer_config.json +120 -7
added_tokens.json
CHANGED
|
@@ -2,5 +2,20 @@
|
|
| 2 |
"<bot>:": 50260,
|
| 3 |
"<endoftext>": 50259,
|
| 4 |
"<pad>": 50257,
|
| 5 |
-
"<startoftext>": 50258
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 2 |
"<bot>:": 50260,
|
| 3 |
"<endoftext>": 50259,
|
| 4 |
"<pad>": 50257,
|
| 5 |
+
"<startoftext>": 50258,
|
| 6 |
+
"beauty": 50263,
|
| 7 |
+
"dreams": 50261,
|
| 8 |
+
"fear": 50264,
|
| 9 |
+
"friendship": 50273,
|
| 10 |
+
"happiness": 50267,
|
| 11 |
+
"hope": 50272,
|
| 12 |
+
"inspirational": 50270,
|
| 13 |
+
"leadership": 50271,
|
| 14 |
+
"motivational": 50269,
|
| 15 |
+
"philosophy": 50262,
|
| 16 |
+
"poetry": 50275,
|
| 17 |
+
"relationships": 50268,
|
| 18 |
+
"romance": 50274,
|
| 19 |
+
"spirituality": 50265,
|
| 20 |
+
"wisdom": 50266
|
| 21 |
}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"max_length": 50
|
| 34 |
}
|
| 35 |
},
|
| 36 |
-
"transformers_version": "4.
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 33 |
"max_length": 50
|
| 34 |
}
|
| 35 |
},
|
| 36 |
+
"transformers_version": "4.39.3",
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 50276
|
| 39 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
"pad_token_id": 50259,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
"pad_token_id": 50259,
|
| 6 |
+
"transformers_version": "4.39.3"
|
| 7 |
}
|
special_tokens_map.json
CHANGED
|
@@ -20,11 +20,5 @@
|
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
-
"unk_token":
|
| 24 |
-
"content": "<|endoftext|>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": true,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
}
|
| 30 |
}
|
|
|
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b30217ff303c3742ce82caa760ff14a33a9869a3b6f39c3b0f89504c0836b38
|
| 3 |
+
size 497993920
|
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
@@ -61,6 +61,141 @@
|
|
| 61 |
"rstrip": false,
|
| 62 |
"normalized": true,
|
| 63 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
}
|
| 65 |
],
|
| 66 |
"normalizer": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 100,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 100
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 61 |
"rstrip": false,
|
| 62 |
"normalized": true,
|
| 63 |
"special": false
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"id": 50261,
|
| 67 |
+
"content": "dreams",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"special": false
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"id": 50262,
|
| 76 |
+
"content": "philosophy",
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"id": 50263,
|
| 85 |
+
"content": "beauty",
|
| 86 |
+
"single_word": false,
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"id": 50264,
|
| 94 |
+
"content": "fear",
|
| 95 |
+
"single_word": false,
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"normalized": true,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"id": 50265,
|
| 103 |
+
"content": "spirituality",
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"normalized": true,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"id": 50266,
|
| 112 |
+
"content": "wisdom",
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"lstrip": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"normalized": true,
|
| 117 |
+
"special": false
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"id": 50267,
|
| 121 |
+
"content": "happiness",
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"lstrip": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"normalized": true,
|
| 126 |
+
"special": false
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"id": 50268,
|
| 130 |
+
"content": "relationships",
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"special": false
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"id": 50269,
|
| 139 |
+
"content": "motivational",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"special": false
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"id": 50270,
|
| 148 |
+
"content": "inspirational",
|
| 149 |
+
"single_word": false,
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"id": 50271,
|
| 157 |
+
"content": "leadership",
|
| 158 |
+
"single_word": false,
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"id": 50272,
|
| 166 |
+
"content": "hope",
|
| 167 |
+
"single_word": false,
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"normalized": true,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"id": 50273,
|
| 175 |
+
"content": "friendship",
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"lstrip": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"normalized": true,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"id": 50274,
|
| 184 |
+
"content": "romance",
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"lstrip": false,
|
| 187 |
+
"rstrip": false,
|
| 188 |
+
"normalized": true,
|
| 189 |
+
"special": false
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"id": 50275,
|
| 193 |
+
"content": "poetry",
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"lstrip": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"normalized": true,
|
| 198 |
+
"special": false
|
| 199 |
}
|
| 200 |
],
|
| 201 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -40,20 +40,133 @@
|
|
| 40 |
"rstrip": false,
|
| 41 |
"single_word": false,
|
| 42 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
}
|
| 44 |
},
|
| 45 |
"bos_token": "<startoftext>",
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"eos_token": "<endoftext>",
|
| 48 |
-
"max_length": 128,
|
| 49 |
"model_max_length": 1024,
|
| 50 |
-
"pad_to_multiple_of": null,
|
| 51 |
"pad_token": "<pad>",
|
| 52 |
-
"pad_token_type_id": 0,
|
| 53 |
-
"padding_side": "right",
|
| 54 |
-
"stride": 0,
|
| 55 |
"tokenizer_class": "GPT2Tokenizer",
|
| 56 |
-
"truncation_side": "right",
|
| 57 |
-
"truncation_strategy": "longest_first",
|
| 58 |
"unk_token": "<|endoftext|>"
|
| 59 |
}
|
|
|
|
| 40 |
"rstrip": false,
|
| 41 |
"single_word": false,
|
| 42 |
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": "dreams",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": "philosophy",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": "beauty",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": "fear",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": "spirituality",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": "wisdom",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": "happiness",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": "relationships",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": "motivational",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": "inspirational",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": "leadership",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": "hope",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": "friendship",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": "romance",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": "poetry",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
}
|
| 164 |
},
|
| 165 |
"bos_token": "<startoftext>",
|
| 166 |
"clean_up_tokenization_spaces": true,
|
| 167 |
"eos_token": "<endoftext>",
|
|
|
|
| 168 |
"model_max_length": 1024,
|
|
|
|
| 169 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
|
|
|
| 170 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 171 |
"unk_token": "<|endoftext|>"
|
| 172 |
}
|