arthu1 commited on
Commit
c2591ac
·
verified ·
1 Parent(s): b61966e

Upload corrected Forge-1-Mini checkpoint and fix tokenizer

Browse files
config.json CHANGED
@@ -29,4 +29,4 @@
29
  "transformers_version": "5.12.0",
30
  "use_cache": true,
31
  "vocab_size": 1024
32
- }
 
29
  "transformers_version": "5.12.0",
30
  "use_cache": true,
31
  "vocab_size": 1024
32
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf09eb69eaee233bfb79cfd8e1cc8f0db48187c19d29d4d71c194f0a26f56d0b
3
  size 20768280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a784e2193a87e7d5a6f6ff30280d3120b02a51d03c11bf4996522c4b988790e
3
  size 20768280
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>",
5
+ "pad_token": "<pad>",
6
+ "additional_special_tokens": [
7
+ "<|im_start|>",
8
+ "<|im_end|>"
9
+ ]
10
+ }
tokenizer.json DELETED
@@ -1,116 +0,0 @@
1
- {
2
- "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
5
- "added_tokens": [
6
- {
7
- "id": 0,
8
- "content": "<unk>",
9
- "single_word": false,
10
- "lstrip": false,
11
- "rstrip": false,
12
- "normalized": false,
13
- "special": true
14
- },
15
- {
16
- "id": 1,
17
- "content": "<s>",
18
- "single_word": false,
19
- "lstrip": false,
20
- "rstrip": false,
21
- "normalized": false,
22
- "special": true
23
- },
24
- {
25
- "id": 2,
26
- "content": "</s>",
27
- "single_word": false,
28
- "lstrip": false,
29
- "rstrip": false,
30
- "normalized": false,
31
- "special": true
32
- },
33
- {
34
- "id": 3,
35
- "content": "<pad>",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": false,
40
- "special": true
41
- }
42
- ],
43
- "normalizer": null,
44
- "pre_tokenizer": {
45
- "type": "Metaspace",
46
- "replacement": "▁",
47
- "prepend_scheme": "first",
48
- "split": false
49
- },
50
- "post_processor": {
51
- "type": "TemplateProcessing",
52
- "single": [
53
- {
54
- "Sequence": {
55
- "id": "A",
56
- "type_id": 0
57
- }
58
- }
59
- ],
60
- "pair": [
61
- {
62
- "Sequence": {
63
- "id": "A",
64
- "type_id": 0
65
- }
66
- },
67
- {
68
- "Sequence": {
69
- "id": "B",
70
- "type_id": 1
71
- }
72
- }
73
- ],
74
- "special_tokens": {}
75
- },
76
- "decoder": {
77
- "type": "Sequence",
78
- "decoders": [
79
- {
80
- "type": "Replace",
81
- "pattern": {
82
- "String": "▁"
83
- },
84
- "content": " "
85
- },
86
- {
87
- "type": "ByteFallback"
88
- },
89
- {
90
- "type": "Fuse"
91
- },
92
- {
93
- "type": "Strip",
94
- "content": " ",
95
- "start": 1,
96
- "stop": 0
97
- }
98
- ]
99
- },
100
- "model": {
101
- "type": "BPE",
102
- "dropout": null,
103
- "unk_token": null,
104
- "continuing_subword_prefix": null,
105
- "end_of_word_suffix": null,
106
- "fuse_unk": true,
107
- "byte_fallback": true,
108
- "ignore_merges": false,
109
- "vocab": {
110
- "<unk>": 0,
111
- "<s>": 1,
112
- "</s>": 2
113
- },
114
- "merges": []
115
- }
116
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feadf1ff141938c8dfee3adea7c787bf474c65d1e040ade69336ddde6bf35d4a
3
+ size 255224
tokenizer_config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "add_prefix_space": null,
3
- "backend": "tokenizers",
4
  "bos_token": "<s>",
5
- "clean_up_tokenization_spaces": false,
6
  "eos_token": "</s>",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "pad_token": "<pad>",
9
- "tokenizer_class": "LlamaTokenizer",
10
  "unk_token": "<unk>",
11
- "use_default_system_prompt": false
12
- }
 
 
 
 
 
1
  {
2
+ "tokenizer_class": "LlamaTokenizer",
3
+ "model_max_length": 512,
4
  "bos_token": "<s>",
 
5
  "eos_token": "</s>",
 
 
 
6
  "unk_token": "<unk>",
7
+ "pad_token": "<pad>",
8
+ "legacy": false,
9
+ "add_bos_token": false,
10
+ "add_eos_token": false,
11
+ "chat_template": "{% for message in messages %}<|im_start|>{{ message['role'] }}\n{{ message['content'] }}\n<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
12
+ }