resave after remoing "use_fast=False"
Browse files- tokenizer.json +9 -0
- tokenizer_config.json +3 -7
tokenizer.json
CHANGED
|
@@ -29,6 +29,15 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 32000,
|
| 35 |
+
"content": "[PAD]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"rstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -8,7 +6,7 @@
|
|
| 8 |
"normalized": false,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false,
|
| 11 |
-
"special":
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
|
@@ -16,7 +14,7 @@
|
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
-
"special":
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
|
@@ -24,7 +22,7 @@
|
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
-
"special":
|
| 28 |
},
|
| 29 |
"32000": {
|
| 30 |
"content": "[PAD]",
|
|
@@ -44,9 +42,7 @@
|
|
| 44 |
"pad_token": "[PAD]",
|
| 45 |
"padding_side": "right",
|
| 46 |
"sp_model_kwargs": {},
|
| 47 |
-
"spaces_between_special_tokens": false,
|
| 48 |
"tokenizer_class": "LlamaTokenizer",
|
| 49 |
-
"tokenizer_file": "/Jupyter/huggingface/.cache/models--meta-llama--Llama-2-7b-chat-hf/snapshots/08751db2aca9bf2f7f80d2e516117a53d7450235/tokenizer.json",
|
| 50 |
"unk_token": "<unk>",
|
| 51 |
"use_default_system_prompt": true
|
| 52 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
|
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
"content": "<s>",
|
|
|
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
"content": "</s>",
|
|
|
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
},
|
| 27 |
"32000": {
|
| 28 |
"content": "[PAD]",
|
|
|
|
| 42 |
"pad_token": "[PAD]",
|
| 43 |
"padding_side": "right",
|
| 44 |
"sp_model_kwargs": {},
|
|
|
|
| 45 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 46 |
"unk_token": "<unk>",
|
| 47 |
"use_default_system_prompt": true
|
| 48 |
}
|