Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- special_tokens_map.json +37 -7
- tokenizer_config.json +41 -41
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2481263088
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62ab482f1b2b08e746302264cab16536b7e335238fd69e80108859dbf36c902e
|
| 3 |
size 2481263088
|
special_tokens_map.json
CHANGED
|
@@ -1,9 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "<|bos|>",
|
| 3 |
-
"eos_token": "<|eos|>",
|
| 4 |
-
"unk_token": "<|unk|>",
|
| 5 |
-
"pad_token": "<|pad|>",
|
| 6 |
-
"mask_token": "<|mask|>",
|
| 7 |
"additional_special_tokens": [
|
| 8 |
"<|reserved_265|>",
|
| 9 |
"<|reserved_266|>",
|
|
@@ -28,5 +23,40 @@
|
|
| 28 |
"<|reserved_285|>",
|
| 29 |
"<|reserved_286|>",
|
| 30 |
"<|reserved_287|>"
|
| 31 |
-
]
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"additional_special_tokens": [
|
| 3 |
"<|reserved_265|>",
|
| 4 |
"<|reserved_266|>",
|
|
|
|
| 23 |
"<|reserved_285|>",
|
| 24 |
"<|reserved_286|>",
|
| 25 |
"<|reserved_287|>"
|
| 26 |
+
],
|
| 27 |
+
"bos_token": {
|
| 28 |
+
"content": "<|bos|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"eos_token": {
|
| 35 |
+
"content": "<|eos|>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
},
|
| 41 |
+
"mask_token": {
|
| 42 |
+
"content": "<|mask|>",
|
| 43 |
+
"lstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"single_word": false
|
| 47 |
+
},
|
| 48 |
+
"pad_token": {
|
| 49 |
+
"content": "<|pad|>",
|
| 50 |
+
"lstrip": false,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"single_word": false
|
| 54 |
+
},
|
| 55 |
+
"unk_token": {
|
| 56 |
+
"content": "<|unk|>",
|
| 57 |
+
"lstrip": false,
|
| 58 |
+
"normalized": false,
|
| 59 |
+
"rstrip": false,
|
| 60 |
+
"single_word": false
|
| 61 |
+
}
|
| 62 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,45 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 3 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
-
"padding_side": "right",
|
| 5 |
-
"truncation_side": "right",
|
| 6 |
-
"bos_token": "<|bos|>",
|
| 7 |
-
"eos_token": "<|eos|>",
|
| 8 |
-
"unk_token": "<|unk|>",
|
| 9 |
-
"pad_token": "<|pad|>",
|
| 10 |
-
"mask_token": "<|mask|>",
|
| 11 |
"add_bos_token": false,
|
| 12 |
"add_eos_token": false,
|
| 13 |
-
"clean_up_tokenization_spaces": true,
|
| 14 |
-
"legacy": false,
|
| 15 |
-
"name_or_path": "custom_autotokenizer_byte_tokenizer",
|
| 16 |
-
"trust_remote_code": false,
|
| 17 |
-
"use_fast": true,
|
| 18 |
-
"additional_special_tokens": [
|
| 19 |
-
"<|reserved_265|>",
|
| 20 |
-
"<|reserved_266|>",
|
| 21 |
-
"<|reserved_267|>",
|
| 22 |
-
"<|reserved_268|>",
|
| 23 |
-
"<|reserved_269|>",
|
| 24 |
-
"<|reserved_270|>",
|
| 25 |
-
"<|reserved_271|>",
|
| 26 |
-
"<|reserved_272|>",
|
| 27 |
-
"<|reserved_273|>",
|
| 28 |
-
"<|reserved_274|>",
|
| 29 |
-
"<|reserved_275|>",
|
| 30 |
-
"<|reserved_276|>",
|
| 31 |
-
"<|reserved_277|>",
|
| 32 |
-
"<|reserved_278|>",
|
| 33 |
-
"<|reserved_279|>",
|
| 34 |
-
"<|reserved_280|>",
|
| 35 |
-
"<|reserved_281|>",
|
| 36 |
-
"<|reserved_282|>",
|
| 37 |
-
"<|reserved_283|>",
|
| 38 |
-
"<|reserved_284|>",
|
| 39 |
-
"<|reserved_285|>",
|
| 40 |
-
"<|reserved_286|>",
|
| 41 |
-
"<|reserved_287|>"
|
| 42 |
-
],
|
| 43 |
"added_tokens_decoder": {
|
| 44 |
"256": {
|
| 45 |
"content": "<|pad|>",
|
|
@@ -297,5 +258,44 @@
|
|
| 297 |
"single_word": false,
|
| 298 |
"special": true
|
| 299 |
}
|
| 300 |
-
}
|
| 301 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"256": {
|
| 6 |
"content": "<|pad|>",
|
|
|
|
| 258 |
"single_word": false,
|
| 259 |
"special": true
|
| 260 |
}
|
| 261 |
+
},
|
| 262 |
+
"additional_special_tokens": [
|
| 263 |
+
"<|reserved_265|>",
|
| 264 |
+
"<|reserved_266|>",
|
| 265 |
+
"<|reserved_267|>",
|
| 266 |
+
"<|reserved_268|>",
|
| 267 |
+
"<|reserved_269|>",
|
| 268 |
+
"<|reserved_270|>",
|
| 269 |
+
"<|reserved_271|>",
|
| 270 |
+
"<|reserved_272|>",
|
| 271 |
+
"<|reserved_273|>",
|
| 272 |
+
"<|reserved_274|>",
|
| 273 |
+
"<|reserved_275|>",
|
| 274 |
+
"<|reserved_276|>",
|
| 275 |
+
"<|reserved_277|>",
|
| 276 |
+
"<|reserved_278|>",
|
| 277 |
+
"<|reserved_279|>",
|
| 278 |
+
"<|reserved_280|>",
|
| 279 |
+
"<|reserved_281|>",
|
| 280 |
+
"<|reserved_282|>",
|
| 281 |
+
"<|reserved_283|>",
|
| 282 |
+
"<|reserved_284|>",
|
| 283 |
+
"<|reserved_285|>",
|
| 284 |
+
"<|reserved_286|>",
|
| 285 |
+
"<|reserved_287|>"
|
| 286 |
+
],
|
| 287 |
+
"bos_token": "<|bos|>",
|
| 288 |
+
"clean_up_tokenization_spaces": true,
|
| 289 |
+
"eos_token": "<|eos|>",
|
| 290 |
+
"extra_special_tokens": {},
|
| 291 |
+
"legacy": false,
|
| 292 |
+
"mask_token": "<|mask|>",
|
| 293 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 294 |
+
"pad_token": "<|pad|>",
|
| 295 |
+
"padding_side": "right",
|
| 296 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 297 |
+
"truncation_side": "right",
|
| 298 |
+
"trust_remote_code": false,
|
| 299 |
+
"unk_token": "<|unk|>",
|
| 300 |
+
"use_fast": true
|
| 301 |
+
}
|