OzzyGT HF Staff commited on
Commit
afe9335
·
verified ·
1 Parent(s): d414829

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +124 -0
  2. generation_config.json +11 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "dtype": "bfloat16",
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": [
9
+ 1,
10
+ 106
11
+ ],
12
+ "image_token_index": 262144,
13
+ "initializer_range": 0.02,
14
+ "mm_tokens_per_image": 256,
15
+ "model_type": "gemma3",
16
+ "text_config": {
17
+ "_sliding_window_pattern": 6,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "bos_token_id": 2,
22
+ "cache_implementation": "hybrid",
23
+ "dtype": "bfloat16",
24
+ "eos_token_id": 1,
25
+ "final_logit_softcapping": null,
26
+ "head_dim": 256,
27
+ "hidden_activation": "gelu_pytorch_tanh",
28
+ "hidden_size": 3840,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 15360,
31
+ "layer_types": [
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "full_attention"
80
+ ],
81
+ "max_position_embeddings": 131072,
82
+ "model_type": "gemma3_text",
83
+ "num_attention_heads": 16,
84
+ "num_hidden_layers": 48,
85
+ "num_key_value_heads": 8,
86
+ "pad_token_id": 0,
87
+ "query_pre_attn_scalar": 256,
88
+ "rms_norm_eps": 1e-06,
89
+ "rope_parameters": {
90
+ "full_attention": {
91
+ "factor": 8.0,
92
+ "rope_theta": 1000000,
93
+ "rope_type": "linear"
94
+ },
95
+ "sliding_attention": {
96
+ "rope_theta": 10000,
97
+ "rope_type": "default"
98
+ }
99
+ },
100
+ "sliding_window": 1024,
101
+ "sliding_window_pattern": 6,
102
+ "tie_word_embeddings": true,
103
+ "use_bidirectional_attention": false,
104
+ "use_cache": true,
105
+ "vocab_size": 262208
106
+ },
107
+ "tie_word_embeddings": true,
108
+ "transformers_version": "5.1.0",
109
+ "vision_config": {
110
+ "attention_dropout": 0.0,
111
+ "dtype": "bfloat16",
112
+ "hidden_act": "gelu_pytorch_tanh",
113
+ "hidden_size": 1152,
114
+ "image_size": 896,
115
+ "intermediate_size": 4304,
116
+ "layer_norm_eps": 1e-06,
117
+ "model_type": "siglip_vision_model",
118
+ "num_attention_heads": 16,
119
+ "num_channels": 3,
120
+ "num_hidden_layers": 27,
121
+ "patch_size": 14,
122
+ "vision_use_head": false
123
+ }
124
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cache_implementation": "hybrid",
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106
7
+ ],
8
+ "top_k": 64,
9
+ "top_p": 0.95,
10
+ "transformers_version": "5.1.0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b5c4675ac66237bb7f5554a0376679e55c006e30b261143ae2903cf00e846c
3
+ size 24374794824