Hugging Face's logo

tirthadagr8
/
CustomOCR

Safetensors
vision-encoder-decoder
Model card Files
xet
Community
tirthadagr8 commited on
Commit
f765426
·
verified ·
1 Parent(s): 0176dda

Upload 17 files

Browse files
Files changed (8) hide show
  1. added_tokens.json +1 -1
  2. checkpoint-30000/config.json +1 -1
  3. checkpoint-30000/generation_config.json +1 -1
  4. config.json +1 -1
  5. generation_config.json +1 -1
  6. tokenizer.json +3 -3
  7. tokenizer_config.json +2 -2
  8. vocab.json +0 -0
added_tokens.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "<|bos|>": 12561,
3
  "<|eos|>": 12562,
4
- "<|pad|>": 12563,
5
  "[PAD]": 12560
6
  }
 
1
  {
2
  "<|bos|>": 12561,
3
  "<|eos|>": 12562,
4
+ "<|endoftext|>": 12563,
5
  "[PAD]": 12560
6
  }
checkpoint-30000/config.json CHANGED
@@ -54,7 +54,7 @@
54
  "output_attentions": false,
55
  "output_hidden_states": false,
56
  "output_scores": false,
57
- "pad_token_id": 12563,
58
  "prefix": null,
59
  "problem_type": null,
60
  "pruned_heads": {},
 
54
  "output_attentions": false,
55
  "output_hidden_states": false,
56
  "output_scores": false,
57
+ "pad_token_id": 0,
58
  "prefix": null,
59
  "problem_type": null,
60
  "pruned_heads": {},
checkpoint-30000/generation_config.json CHANGED
@@ -7,7 +7,7 @@
7
  "max_length": 64,
8
  "no_repeat_ngram_size": 3,
9
  "num_beams": 5,
10
- "pad_token_id": 12563,
11
  "transformers_version": "4.47.0",
12
  "use_cache": false
13
  }
 
7
  "max_length": 64,
8
  "no_repeat_ngram_size": 3,
9
  "num_beams": 5,
10
+ "pad_token_id": 0,
11
  "transformers_version": "4.47.0",
12
  "use_cache": false
13
  }
config.json CHANGED
@@ -54,7 +54,7 @@
54
  "output_attentions": false,
55
  "output_hidden_states": false,
56
  "output_scores": false,
57
- "pad_token_id": 12563,
58
  "prefix": null,
59
  "problem_type": null,
60
  "pruned_heads": {},
 
54
  "output_attentions": false,
55
  "output_hidden_states": false,
56
  "output_scores": false,
57
+ "pad_token_id": 0,
58
  "prefix": null,
59
  "problem_type": null,
60
  "pruned_heads": {},
generation_config.json CHANGED
@@ -7,7 +7,7 @@
7
  "max_length": 64,
8
  "no_repeat_ngram_size": 3,
9
  "num_beams": 5,
10
- "pad_token_id": 12563,
11
  "transformers_version": "4.47.0",
12
  "use_cache": false
13
  }
 
7
  "max_length": 64,
8
  "no_repeat_ngram_size": 3,
9
  "num_beams": 5,
10
+ "pad_token_id": 0,
11
  "transformers_version": "4.47.0",
12
  "use_cache": false
13
  }
tokenizer.json CHANGED
@@ -5,7 +5,7 @@
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
- "content": "<|endoftext|>",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
@@ -41,7 +41,7 @@
41
  },
42
  {
43
  "id": 12563,
44
- "content": "<|pad|>",
45
  "single_word": false,
46
  "lstrip": false,
47
  "rstrip": false,
@@ -78,7 +78,7 @@
78
  "byte_fallback": false,
79
  "ignore_merges": false,
80
  "vocab": {
81
- "<|endoftext|>": 0,
82
  "!": 1,
83
  "\"": 2,
84
  "#": 3,
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
+ "content": "<|pad|>",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
 
41
  },
42
  {
43
  "id": 12563,
44
+ "content": "<|endoftext|>",
45
  "single_word": false,
46
  "lstrip": false,
47
  "rstrip": false,
 
78
  "byte_fallback": false,
79
  "ignore_merges": false,
80
  "vocab": {
81
+ "<|pad|>": 0,
82
  "!": 1,
83
  "\"": 2,
84
  "#": 3,
tokenizer_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {
7
- "content": "<|endoftext|>",
8
  "lstrip": false,
9
  "normalized": true,
10
  "rstrip": false,
@@ -36,7 +36,7 @@
36
  "special": true
37
  },
38
  "12563": {
39
- "content": "<|pad|>",
40
  "lstrip": false,
41
  "normalized": false,
42
  "rstrip": false,
 
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {
7
+ "content": "<|pad|>",
8
  "lstrip": false,
9
  "normalized": true,
10
  "rstrip": false,
 
36
  "special": true
37
  },
38
  "12563": {
39
+ "content": "<|endoftext|>",
40
  "lstrip": false,
41
  "normalized": false,
42
  "rstrip": false,
vocab.json CHANGED
The diff for this file is too large to render. See raw diff