MuXodious commited on
Commit
9c65bd1
·
verified ·
1 Parent(s): 57742ff

Upload tokenizers

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end_of_image>": 262145,
3
+ "<image_soft_token>": 262144
4
+ }
config.json CHANGED
@@ -8,10 +8,7 @@
8
  "attn_logit_softcapping": null,
9
  "bos_token_id": 2,
10
  "dtype": "bfloat16",
11
- "eos_token_id": [
12
- 1,
13
- 50
14
- ],
15
  "final_logit_softcapping": null,
16
  "head_dim": 256,
17
  "hidden_activation": "gelu_pytorch_tanh",
@@ -46,19 +43,10 @@
46
  "pad_token_id": 0,
47
  "query_pre_attn_scalar": 256,
48
  "rms_norm_eps": 1e-06,
49
- "rope_parameters": {
50
- "full_attention": {
51
- "rope_theta": 1000000.0,
52
- "rope_type": "default"
53
- },
54
- "sliding_attention": {
55
- "rope_theta": 10000.0,
56
- "rope_type": "default"
57
- }
58
- },
59
  "sliding_window": 512,
60
- "tie_word_embeddings": true,
61
- "transformers_version": "5.0.0.dev0",
62
  "use_bidirectional_attention": false,
63
  "use_cache": true,
64
  "vocab_size": 262144
 
8
  "attn_logit_softcapping": null,
9
  "bos_token_id": 2,
10
  "dtype": "bfloat16",
11
+ "eos_token_id": [1, 50],
 
 
 
12
  "final_logit_softcapping": null,
13
  "head_dim": 256,
14
  "hidden_activation": "gelu_pytorch_tanh",
 
43
  "pad_token_id": 0,
44
  "query_pre_attn_scalar": 256,
45
  "rms_norm_eps": 1e-06,
46
+ "rope_local_base_freq": 10000.0,
47
+ "rope_theta": 1000000.0,
 
 
 
 
 
 
 
 
48
  "sliding_window": 512,
49
+ "transformers_version": "4.57.3",
 
50
  "use_bidirectional_attention": false,
51
  "use_cache": true,
52
  "vocab_size": 262144
generation_config.json CHANGED
@@ -8,5 +8,5 @@
8
  ],
9
  "top_k": 64,
10
  "top_p": 0.95,
11
- "transformers_version": "5.0.0.dev0"
12
  }
 
8
  ],
9
  "top_k": 64,
10
  "top_p": 0.95,
11
+ "transformers_version": "4.57.3"
12
  }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "sfr_token": "<start_function_response>",
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3655797f9d732b7dc08b4225200697af8e37d94b74711d9b1d8166feb953578
3
- size 33384774
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab06510581429a52484f103c9df074578506a025c40db1197d3625041566ca7
3
+ size 33384901
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff