vox-machina-inc commited on
Commit
88bf43b
·
1 Parent(s): 25a0fe1

fix(tokenizer): fix it

Browse files
generation_config.json CHANGED
@@ -1,9 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 100257,
4
- "eos_token_id": [
5
- 100257,
6
- 100265
7
- ],
8
- "transformers_version": "4.47.0"
9
- }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 100257,
4
+ "eos_token_id": 100265,
5
+ "pad_token_id": 100351,
6
+ "transformers_version": "4.47.1"
7
+ }
 
 
special_tokens_map.json CHANGED
@@ -7,18 +7,18 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|endoftext|>",
11
  "lstrip": true,
12
  "normalized": false,
13
  "rstrip": true,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|endoftext|>",
18
  "lstrip": true,
19
  "normalized": false,
20
  "rstrip": true,
21
  "single_word": false
22
  },
23
- "unk_token": "<|endoftext|>"
24
- }
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|im_end|>",
11
  "lstrip": true,
12
  "normalized": false,
13
  "rstrip": true,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "<|dummy_87|>",
18
  "lstrip": true,
19
  "normalized": false,
20
  "rstrip": true,
21
  "single_word": false
22
  },
23
+ "unk_token": "�"
24
+ }
tokenizer.json CHANGED
@@ -3,6 +3,15 @@
3
  "truncation": null,
4
  "padding": null,
5
  "added_tokens": [
 
 
 
 
 
 
 
 
 
6
  {
7
  "id": 100256,
8
  "content": "<|dummy_0|>",
 
3
  "truncation": null,
4
  "padding": null,
5
  "added_tokens": [
6
+ {
7
+ "id": 5809,
8
+ "content": "�",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
  {
16
  "id": 100256,
17
  "content": "<|dummy_0|>",
tokenizer_config.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
4
  "100256": {
5
  "content": "<|dummy_0|>",
6
  "lstrip": true,
@@ -771,12 +779,13 @@
771
  }
772
  },
773
  "bos_token": "<|endoftext|>",
774
- "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
775
  "clean_up_tokenization_spaces": false,
776
- "eos_token": "<|endoftext|>",
777
  "extra_special_tokens": {},
778
  "model_max_length": 16384,
779
- "pad_token": "<|endoftext|>",
 
780
  "tokenizer_class": "GPT2Tokenizer",
781
- "unk_token": "<|endoftext|>"
782
- }
 
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "5809": {
5
+ "content": "�",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
  "100256": {
13
  "content": "<|dummy_0|>",
14
  "lstrip": true,
 
779
  }
780
  },
781
  "bos_token": "<|endoftext|>",
782
+ "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
783
  "clean_up_tokenization_spaces": false,
784
+ "eos_token": "<|im_end|>",
785
  "extra_special_tokens": {},
786
  "model_max_length": 16384,
787
+ "pad_token": "<|dummy_87|>",
788
+ "padding_side": "left",
789
  "tokenizer_class": "GPT2Tokenizer",
790
+ "unk_token": "�"
791
+ }