Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +12 -5
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -28,16 +27,24 @@
|
|
28 |
"special": true
|
29 |
}
|
30 |
},
|
|
|
31 |
"bos_token": "<s>",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
|
|
33 |
"eos_token": "</s>",
|
34 |
-
"
|
35 |
-
"
|
|
|
|
|
|
|
|
|
36 |
"pad_token": "<unk>",
|
37 |
"padding_side": "left",
|
38 |
-
"
|
39 |
-
"
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
41 |
"unk_token": "<unk>",
|
42 |
"use_default_system_prompt": false
|
43 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
+
"chat_template": null,
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
+
"cls_token": null,
|
35 |
"eos_token": "</s>",
|
36 |
+
"mask_token": null,
|
37 |
+
"model_input_names": [
|
38 |
+
"input_ids",
|
39 |
+
"attention_mask"
|
40 |
+
],
|
41 |
+
"model_max_length": 16384,
|
42 |
"pad_token": "<unk>",
|
43 |
"padding_side": "left",
|
44 |
+
"sep_token": null,
|
45 |
+
"split_special_tokens": false,
|
46 |
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"truncation_side": "right",
|
48 |
"unk_token": "<unk>",
|
49 |
"use_default_system_prompt": false
|
50 |
}
|