updating tokenizers
Browse files- modeling_gpt2.py +0 -3
- special_tokens_map.json +0 -5
- tokenizer.json +0 -0
- tokenizer_config.json +0 -9
- vocab.json +0 -0
modeling_gpt2.py
CHANGED
@@ -48,9 +48,6 @@ from transformers.utils import (
|
|
48 |
from transformers.utils.model_parallel_utils import assert_device_map, get_device_map
|
49 |
from .configuration_gpt2 import GPT2Config
|
50 |
|
51 |
-
##let's test again
|
52 |
-
|
53 |
-
|
54 |
logger = logging.get_logger(__name__)
|
55 |
|
56 |
_CHECKPOINT_FOR_DOC = "gpt2"
|
|
|
48 |
from transformers.utils.model_parallel_utils import assert_device_map, get_device_map
|
49 |
from .configuration_gpt2 import GPT2Config
|
50 |
|
|
|
|
|
|
|
51 |
logger = logging.get_logger(__name__)
|
52 |
|
53 |
_CHECKPOINT_FOR_DOC = "gpt2"
|
special_tokens_map.json
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<|endoftext|>",
|
3 |
-
"eos_token": "<|endoftext|>",
|
4 |
-
"unk_token": "<|endoftext|>"
|
5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": "<|endoftext|>",
|
4 |
-
"clean_up_tokenization_spaces": true,
|
5 |
-
"eos_token": "<|endoftext|>",
|
6 |
-
"model_max_length": 1024,
|
7 |
-
"tokenizer_class": "GPT2Tokenizer",
|
8 |
-
"unk_token": "<|endoftext|>"
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|