tokenizer_config.json
1.2 KB · 54 lines · json Raw
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 "32000": {
30 "content": "<PAD>",
31 "lstrip": false,
32 "normalized": false,
33 "rstrip": false,
34 "single_word": false,
35 "special": true
36 }
37 },
38 "auto_map": {
39 "AutoProcessor": "processing_prismatic.PrismaticProcessor"
40 },
41 "bos_token": "<s>",
42 "clean_up_tokenization_spaces": false,
43 "eos_token": "</s>",
44 "legacy": false,
45 "model_max_length": 2048,
46 "pad_token": "<PAD>",
47 "padding_side": "right",
48 "processor_class": "PrismaticProcessor",
49 "sp_model_kwargs": {},
50 "tokenizer_class": "LlamaTokenizer",
51 "unk_token": "<unk>",
52 "use_default_system_prompt": false
53 }
54