tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +3 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
@@ -317,7 +318,9 @@
|
|
| 317 |
"bos_token": "<|endoftext|>",
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 320 |
"model_max_length": 2048,
|
|
|
|
| 321 |
"return_token_type_ids": false,
|
| 322 |
"tokenizer_class": "CodeGenTokenizer",
|
| 323 |
"unk_token": "<|endoftext|>"
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
|
|
| 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": null,
|
| 324 |
"return_token_type_ids": false,
|
| 325 |
"tokenizer_class": "CodeGenTokenizer",
|
| 326 |
"unk_token": "<|endoftext|>"
|