jburtoft commited on
Commit
b2f00ab
1 Parent(s): c4eaa0c

Upload folder using huggingface_hub (#2)

Browse files

- 6cf690c92a5179db9f8676ed9c427654777b09fce653df820727f1a363ed29e1 (e2d913a5e218584fdfdabf8d9ee5467831ffca0a)
- f4b397c1183e04242c7dfa64fddb9809c58c7b0de9f4962f48aec1812d509eaa (2c2e48fbe4cfd28272cadaa8375d9f63660fa794)
- 6512125ab32f0a1649265d71fca8f677076d0207c44a6140b451e3ea03e8223c (994cafdfb25e34b163ef328bf250af591310908b)
- 163dbae62932ee7833eebf26c387dc2fbd3eda0892446b45291dfcc5d14c19ad (7ed5d2e8f89d23fe2b8c3dc79f1a92c144f79b8c)
- 794be9d05ceafdab568a3caab72cc6164fe3fc2dab4f0aa2309213afef54efb1 (f62b790bc518349c54f3bff2534b373ab7db54a9)
- ba8977eeefec3b0871905c7f18d31118a665c93b375ba9ee736bdda0465cad78 (cbe3c6be64280579e307a3db5f3873ae795de089)
- af9ebd53817549a275b9ae22c3954b8945f15abb72cc4f73000f3fbc546879c1 (dc6c203e1aab95728161216cbb86f93887781482)
- 630b22f0b14b9a5a57637feaea99d1e769a36f6e9a7618bcaf8632ee0d9f3d1c (a29b0f345a7b23a1e25bf9688d72231d45987618)
- 7072e292695efb5dff0e1ca6faeeaab2319b4539ff9305d2a31f4c4194a8d584 (d4a2a202511c453c6525b0a0429a945b2d48aeb9)
- 658c0b4b261ac96898575718d25766fe780cff28f782a76e2937485484084368 (eee270c7e2b8b9a988a7554f6e8f464f689b610c)
- f4f1c1e67f078727f9ceea6d333912acba53e0ddc8a0e3d74eb0d153be9e98a5 (3fccec7218487aa3d88fe71103ac3ed74b0658c7)
- b6a18a0689389e44e4a73a5f14cefcb04d15108e795a4912055b2bdd3eb87d49 (ca6db71c022e76176ea4e6ae6c842182148034d7)
- 4a2b31b58dc02fbb8f137486d9290c0e08817e7a4e036cc75086940e19c1a99d (74078ed0e3c8a06fc6b0006a81b1267b0e7a8bc5)
- 83454115d512a595290d52d8ce98c4d287583dcdbfac76707e8c0969d8ac980b (306f982d2c8fbd0d2d5cc290662d3c2e78a6bfc1)
- c78a658cab35c5f051989be749729d4ebd60c887c8fb5f8e0e1cf9983e2c7487 (57c82b234b514b2ce14f2956b03a7cfcca275bfe)

special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }