lmzheng commited on
Commit
7976eed
1 Parent(s): 163cfea

Update tokenizer config

Browse files
Files changed (3) hide show
  1. config.json +1 -2
  2. special_tokens_map.json +21 -4
  3. tokenizer_config.json +30 -6
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "/home/ubuntu/model_weights/backup/vicuna-13b-20230322-clean-lang-fp16/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -9,7 +8,7 @@
9
  "hidden_size": 5120,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 13824,
12
- "max_sequence_length": 2048,
13
  "model_type": "llama",
14
  "num_attention_heads": 40,
15
  "num_hidden_layers": 40,
 
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
 
8
  "hidden_size": 5120,
9
  "initializer_range": 0.02,
10
  "intermediate_size": 13824,
11
+ "max_position_embeddings": 2048,
12
  "model_type": "llama",
13
  "num_attention_heads": 40,
14
  "num_hidden_layers": 40,
special_tokens_map.json CHANGED
@@ -1,6 +1,23 @@
1
  {
2
- "bos_token": "</s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "</s>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
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_config.json CHANGED
@@ -1,9 +1,33 @@
1
  {
2
- "bos_token": "",
3
- "eos_token": "",
4
- "model_max_length": 2048,
5
- "padding_side": "right",
6
- "special_tokens_map_file": "/home/gcpuser/hf-output/llama-13b/special_tokens_map.json",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "tokenizer_class": "LlamaTokenizer",
8
- "unk_token": ""
 
 
 
 
 
 
 
9
  }
 
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
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
  "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
  }