309d2650584bbf0394e7511be96910ce9a8aa967a60633981afa51e88d275d8d
Browse files- special_tokens_map.json +0 -1
- tokenizer.json +0 -18
- tokenizer_config.json +1 -18
special_tokens_map.json
CHANGED
@@ -13,7 +13,6 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "<pad>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -29,24 +29,6 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 32000,
|
35 |
-
"content": "<pad>",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"special": true
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 32001,
|
44 |
-
"content": "<start_header_id>",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"normalized": true,
|
49 |
-
"special": false
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -25,30 +25,13 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<pad>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<start_header_id>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": false
|
44 |
}
|
45 |
},
|
46 |
"bos_token": "<s>",
|
47 |
-
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
"eos_token": "</s>",
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
51 |
-
"pad_token":
|
52 |
"padding_side": "right",
|
53 |
"sp_model_kwargs": {},
|
54 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
"bos_token": "<s>",
|
|
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "</s>",
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": null,
|
35 |
"padding_side": "right",
|
36 |
"sp_model_kwargs": {},
|
37 |
"tokenizer_class": "LlamaTokenizer",
|