jburtoft commited on
Commit
89529d3
1 Parent(s): f7c32cc

Upload folder using huggingface_hub (#3)

Browse files

- e8ed5629da0a4861487b1bf8c5385fe71e808a2cb0f849ead36f407bb0fa0610 (30efea0b1c86beb81f151e9ef030043f20b9c47f)
- 8685c8a80d7524803d0dd247a0d16f785732f2237554c7aa4ebbd826c35a242b (735d9965ad65852f4e7b2aa016ea3dbaf7938cc2)
- 8f0df90739d90402b4a18c252948f915a3c0b46c5fdfd6d510d7915159500a0e (770c4341825fc59669e0632addf6c97edf4846f2)
- 5ea8ae4b66c2b96996e5272ae2b832b94ce3e60aa5e3a41d71612240888e78be (b42f2d954c4bc3e89502684658a20c3dcf19dce7)
- d1be15f80ba9319496ee91217b3199fcef40726c0c0ec2a17342dd088bf3b9c4 (2125b5056572f13708d02ec3945a8ac75fd43d73)
- 511604691ce5583b8f7941ce59eaab055fa54d147e23411a3435d4ce979dc2b4 (b641cd53584c598a87ba4e6bcddf49bcf85a4222)
- 717c1316d0a17e651b6e09c8b79ff91fe04b3b2e3cf78e60b7f6f24996af85e7 (98e5c92c597ce0847175169b27d463551ddac243)
- 2ef9e0e6fa270c62ec588ba8830c331f39bd830de3ccfb2cd683582006384a6c (8185804489966d774a10ac3128cd5996d3905f50)
- defab67865fba11805e36a141c23ae2c30c9d68a48bf3cd8627425abe6e6ec40 (d0f75b7edee5e6295a63065298ba3010f2a105cc)
- 2af91306f926c3e84b6effb1fcb8d9bcfe67dfce5560bffa96cf3a1ef76c24da (a90a4435360ccfe371e49fdfeba8d5e4d675c171)
- 0b13ca37028a01945c617c1322d4f935ba0ccd820a899ae964fdd8f4631872ee (6476e3af7543127abb28b855a84348009f0ff75b)
- f30dfef0b32e688f7a1e8c8e728e734c9276ca18e5a205a6ef21bad7ea9bd541 (a9f0921f4d3db9bad4c143b702fbe1a63cc97409)
- 74148c1005566e92c07022708b0cd9ee4c09b74c8c197fc829ef2a218973f201 (971c4827abf2e2777b9ccfaba5a4d41eb1283d75)
- 050b59dfd5222d4461356f80838c91dc64f400b8fc6b0c0d2490f92512d15f1f (9b1c8b9c73eaf20cefbc4b58a3e4ac269df05774)

special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
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
Binary file (500 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "CodeLlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }