Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -3
- vocab.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
@@ -318,9 +317,8 @@
|
|
| 318 |
"bos_token": "<|endoftext|>",
|
| 319 |
"clean_up_tokenization_spaces": true,
|
| 320 |
"eos_token": "<|endoftext|>",
|
| 321 |
-
"errors": "replace",
|
| 322 |
"model_max_length": 2048,
|
| 323 |
-
"pad_token":
|
| 324 |
"return_token_type_ids": false,
|
| 325 |
"tokenizer_class": "CodeGenTokenizer",
|
| 326 |
"unk_token": "<|endoftext|>"
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
|
|
| 317 |
"bos_token": "<|endoftext|>",
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 320 |
"model_max_length": 2048,
|
| 321 |
+
"pad_token": "<|endoftext|>",
|
| 322 |
"return_token_type_ids": false,
|
| 323 |
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
"unk_token": "<|endoftext|>"
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|