Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +4 -22
- tokenizer.json +0 -0
- tokenizer_config.json +10 -33
- vocab.json +0 -0
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "</s>",
|
| 17 |
-
"unk_token": {
|
| 18 |
-
"content": "<unk>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,43 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
-
"
|
| 7 |
-
"content": "
|
| 8 |
"lstrip": false,
|
| 9 |
-
"normalized":
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"1": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"2": {
|
| 23 |
-
"content": "</s>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
}
|
| 30 |
},
|
| 31 |
-
"bos_token": "
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
-
"eos_token": "
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"sp_model_kwargs": {},
|
| 39 |
-
"spaces_between_special_tokens": false,
|
| 40 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
-
"unk_token": "<unk>",
|
| 42 |
-
"use_default_system_prompt": false
|
| 43 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
|
|
|
|
|
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
}
|
| 12 |
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"model_max_length": 1024,
|
| 17 |
+
"pad_token": "<|endoftext|>",
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|