Commit
•
88d1834
1
Parent(s):
16d0297
Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +10 -16
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,28 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
| 7 |
-
"lstrip":
|
| 8 |
-
"normalized":
|
| 9 |
-
"rstrip":
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
-
"lstrip":
|
| 16 |
-
"normalized":
|
| 17 |
-
"rstrip":
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
-
"lstrip":
|
| 24 |
-
"normalized":
|
| 25 |
-
"rstrip":
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
}
|
|
@@ -35,11 +33,7 @@
|
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
"pad_token": "<unk>",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
-
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
-
"tokenizer_file": "/N/u/oleykin/BigRed200/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/tokenizer.json",
|
| 41 |
-
"trust_remote_code": false,
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
-
"use_default_system_prompt": true
|
| 44 |
-
"use_fast": true
|
| 45 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
}
|
|
|
|
| 33 |
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
"pad_token": "<unk>",
|
| 35 |
"sp_model_kwargs": {},
|
|
|
|
| 36 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 37 |
"unk_token": "<unk>",
|
| 38 |
+
"use_default_system_prompt": true
|
|
|
|
| 39 |
}
|