Upload tokenizer
Browse files- added_tokens.json +8 -0
- special_tokens_map.json +14 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +74 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\n\n### Instruction:\n": 65107,
|
| 3 |
+
"\n\n### Response:\n": 65108,
|
| 4 |
+
"</s>": 2,
|
| 5 |
+
"<pad>": 65109,
|
| 6 |
+
"<s>": 1,
|
| 7 |
+
"<unk>": 0
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"\n\n### Instruction:\n",
|
| 7 |
+
"\n\n### Response:\n",
|
| 8 |
+
"<pad>"
|
| 9 |
+
],
|
| 10 |
+
"bos_token": "<s>",
|
| 11 |
+
"eos_token": "</s>",
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fca4624723058f2d55a0929b9782c65ccfa810a7605bd3e7c36584519a4f377
|
| 3 |
+
size 1011834
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"65107": {
|
| 30 |
+
"content": "\n\n### Instruction:\n",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": true,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"65108": {
|
| 38 |
+
"content": "\n\n### Response:\n",
|
| 39 |
+
"lstrip": true,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"65109": {
|
| 46 |
+
"content": "<pad>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
"additional_special_tokens": [
|
| 55 |
+
"<unk>",
|
| 56 |
+
"<s>",
|
| 57 |
+
"</s>",
|
| 58 |
+
"\n\n### Instruction:\n",
|
| 59 |
+
"\n\n### Response:\n",
|
| 60 |
+
"<pad>"
|
| 61 |
+
],
|
| 62 |
+
"bos_token": "<s>",
|
| 63 |
+
"clean_up_tokenization_spaces": false,
|
| 64 |
+
"eos_token": "</s>",
|
| 65 |
+
"legacy": true,
|
| 66 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 67 |
+
"pad_token": "<pad>",
|
| 68 |
+
"sp_model_kwargs": {},
|
| 69 |
+
"spaces_between_special_tokens": false,
|
| 70 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 71 |
+
"unk_token": "<unk>",
|
| 72 |
+
"use_default_system_prompt": true,
|
| 73 |
+
"use_fast": true
|
| 74 |
+
}
|