upload tokenizer
Browse files- added_tokens.json +3 -3
- tokenizer.json +3 -3
- tokenizer_config.json +4 -2
added_tokens.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"\n\n### Instruction:\n":
|
| 3 |
-
"\n\n### Response:\n":
|
| 4 |
-
"<pad>":
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"\n\n### Instruction:\n": 60512,
|
| 3 |
+
"\n\n### Response:\n": 60513,
|
| 4 |
+
"<pad>": 60514
|
| 5 |
}
|
tokenizer.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 60512,
|
| 35 |
-
"content": "
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 60513,
|
| 44 |
-
"content": "\n\n###
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
@@ -50,7 +50,7 @@
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 60514,
|
| 53 |
-
"content": "
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 60512,
|
| 35 |
+
"content": "\n\n### Instruction:\n",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 60513,
|
| 44 |
+
"content": "\n\n### Response:\n",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 60514,
|
| 53 |
+
"content": "<pad>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "</s>",
|
|
@@ -19,7 +20,7 @@
|
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"legacy": true,
|
| 22 |
-
"model_max_length":
|
| 23 |
"pad_token": null,
|
| 24 |
"sp_model_kwargs": {},
|
| 25 |
"tokenizer_class": "LlamaTokenizer",
|
|
@@ -30,5 +31,6 @@
|
|
| 30 |
"normalized": true,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false
|
| 33 |
-
}
|
|
|
|
| 34 |
}
|
|
|
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"device_map": "cpu",
|
| 14 |
"eos_token": {
|
| 15 |
"__type": "AddedToken",
|
| 16 |
"content": "</s>",
|
|
|
|
| 20 |
"single_word": false
|
| 21 |
},
|
| 22 |
"legacy": true,
|
| 23 |
+
"model_max_length": 1024,
|
| 24 |
"pad_token": null,
|
| 25 |
"sp_model_kwargs": {},
|
| 26 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 31 |
"normalized": true,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"use_fast": true
|
| 36 |
}
|