ashwinmuthuraman
commited on
Commit
•
a5cc1ac
1
Parent(s):
bae8e3c
Upload tokenizer
Browse files- README.md +1 -1
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert/distilgpt2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- eli5_category
|
|
|
8 |
model-index:
|
9 |
- name: my_awesome_eli5_clm-model
|
10 |
results: []
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- eli5_category
|
7 |
+
base_model: distilbert/distilgpt2
|
8 |
model-index:
|
9 |
- name: my_awesome_eli5_clm-model
|
10 |
results: []
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
|
|
4 |
"unk_token": "<|endoftext|>"
|
5 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
"unk_token": "<|endoftext|>"
|
6 |
}
|
tokenizer_config.json
CHANGED
@@ -14,6 +14,7 @@
|
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
16 |
"model_max_length": 1024,
|
|
|
17 |
"tokenizer_class": "GPT2Tokenizer",
|
18 |
"unk_token": "<|endoftext|>"
|
19 |
}
|
|
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
16 |
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
"tokenizer_class": "GPT2Tokenizer",
|
19 |
"unk_token": "<|endoftext|>"
|
20 |
}
|