Hugging Face's logo

rnaveensrinivas
/
falcon-rw-1b-instruct-openorca-retrained_network_corpus

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
rnaveensrinivas commited on
Commit
9c22739
·
verified ·
1 Parent(s): 0c12fda

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +4 -4
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +10 -33
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,21 +1,21 @@
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
- "pad_token": "</s>",
17
  "unk_token": {
18
- "content": "<unk>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,25 +1,8 @@
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,
@@ -27,17 +10,11 @@
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": "</s>",
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
  }
 
1
  {
2
+ "add_prefix_space": false,
 
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
 
10
  "special": true
11
  }
12
  },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
20
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff