add tokenizer
Browse files- merges.txt +1 -1
- special_tokens_map.json +3 -21
- tokenizer.json +0 -0
- tokenizer_config.json +6 -27
- vocab.json +0 -0
merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"unk_token": {
|
| 17 |
-
"content": "<|endoftext|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": true,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
}
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,31 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
-
"bos_token":
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
-
"eos_token": {
|
| 13 |
-
"__type": "AddedToken",
|
| 14 |
-
"content": "<|endoftext|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": true,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
-
"errors": "replace",
|
| 21 |
-
"pad_token": null,
|
| 22 |
"tokenizer_class": "GPT2Tokenizer",
|
| 23 |
-
"unk_token":
|
| 24 |
-
"__type": "AddedToken",
|
| 25 |
-
"content": "<|endoftext|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": true,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|