Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +0 -2
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -439,7 +438,6 @@
|
|
| 439 |
"bos_token": "<|startoftext|>",
|
| 440 |
"clean_up_tokenization_spaces": false,
|
| 441 |
"eos_token": "<|endoftext|>",
|
| 442 |
-
"extra_special_tokens": {},
|
| 443 |
"fast": true,
|
| 444 |
"legacy": true,
|
| 445 |
"model_max_length": 4096,
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 438 |
"bos_token": "<|startoftext|>",
|
| 439 |
"clean_up_tokenization_spaces": false,
|
| 440 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 441 |
"fast": true,
|
| 442 |
"legacy": true,
|
| 443 |
"model_max_length": 4096,
|