jandonov commited on
Commit
1f70491
·
verified ·
1 Parent(s): 45d92b8

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +177 -3
config.json CHANGED
@@ -1,4 +1,178 @@
1
  {
2
- "module_input_name": "sentence_embedding",
3
- "module_output_name": "sentence_embedding"
4
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "EmbeddingGemma2Model"
4
+ ],
5
+ "audio_config": {
6
+ "_name_or_path": "",
7
+ "architectures": null,
8
+ "attention_chunk_size": 12,
9
+ "attention_context_left": 13,
10
+ "attention_context_right": 0,
11
+ "attention_invalid_logits_value": -1000000000.0,
12
+ "attention_logit_cap": 50.0,
13
+ "chunk_size_feed_forward": 0,
14
+ "conv_kernel_size": 5,
15
+ "dtype": "bfloat16",
16
+ "gradient_clipping": 10000000000.0,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "is_encoder_decoder": false,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1
28
+ },
29
+ "model_type": "gemma4_audio",
30
+ "num_attention_heads": 8,
31
+ "num_hidden_layers": 12,
32
+ "output_attentions": false,
33
+ "output_hidden_states": false,
34
+ "output_proj_dims": 1536,
35
+ "problem_type": null,
36
+ "residual_weight": 0.5,
37
+ "return_dict": true,
38
+ "rms_norm_eps": 1e-06,
39
+ "subsampling_conv_channels": [
40
+ 128,
41
+ 32
42
+ ],
43
+ "use_clipped_linears": true
44
+ },
45
+ "audio_token_id": 258881,
46
+ "boa_token_id": 256000,
47
+ "boi_token_id": 255999,
48
+ "dtype": "bfloat16",
49
+ "eoa_token_index": 258883,
50
+ "eoi_token_id": 258882,
51
+ "image_token_id": 258880,
52
+ "initializer_range": 0.02,
53
+ "model_type": "embedding_gemma2",
54
+ "text_config": {
55
+ "attention_bias": false,
56
+ "attention_dropout": 0.0,
57
+ "bos_token_id": 2,
58
+ "dtype": "bfloat16",
59
+ "embedding_dim": 768,
60
+ "eos_token_id": 1,
61
+ "head_dim": 256,
62
+ "hidden_activation": "gelu_pytorch_tanh",
63
+ "hidden_size": 512,
64
+ "hidden_size_per_layer_input": 512,
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 2048,
67
+ "layer_types": [
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
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "full_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "full_attention"
92
+ ],
93
+ "max_position_embeddings": 262144,
94
+ "model_type": "embedding_gemma2_text",
95
+ "num_attention_heads": 4,
96
+ "num_hidden_layers": 24,
97
+ "num_key_value_heads": 2,
98
+ "pad_token_id": 0,
99
+ "per_layer_config": {
100
+ "05": {
101
+ "head_dim": 512,
102
+ "num_key_value_heads": 1
103
+ },
104
+ "11": {
105
+ "head_dim": 512,
106
+ "num_key_value_heads": 1
107
+ },
108
+ "17": {
109
+ "head_dim": 512,
110
+ "num_key_value_heads": 1
111
+ },
112
+ "23": {
113
+ "head_dim": 512,
114
+ "num_key_value_heads": 1
115
+ }
116
+ },
117
+ "rms_norm_eps": 1e-06,
118
+ "rope_parameters": {
119
+ "full_attention": {
120
+ "partial_rotary_factor": 0.25,
121
+ "rope_theta": 1000000.0,
122
+ "rope_type": "proportional"
123
+ },
124
+ "sliding_attention": {
125
+ "rope_theta": 10000.0,
126
+ "rope_type": "default"
127
+ }
128
+ },
129
+ "sliding_window": 512,
130
+ "vocab_size": 262144
131
+ },
132
+ "transformers_version": "5.18.0.dev0",
133
+ "video_token_id": 258884,
134
+ "vision_config": {
135
+ "_name_or_path": "",
136
+ "architectures": null,
137
+ "attention_bias": false,
138
+ "attention_dropout": 0.0,
139
+ "chunk_size_feed_forward": 0,
140
+ "default_output_length": 280,
141
+ "dtype": "bfloat16",
142
+ "global_head_dim": 64,
143
+ "head_dim": 64,
144
+ "hidden_activation": "gelu_pytorch_tanh",
145
+ "hidden_size": 768,
146
+ "id2label": {
147
+ "0": "LABEL_0",
148
+ "1": "LABEL_1"
149
+ },
150
+ "initializer_range": 0.02,
151
+ "intermediate_size": 3072,
152
+ "is_encoder_decoder": false,
153
+ "label2id": {
154
+ "LABEL_0": 0,
155
+ "LABEL_1": 1
156
+ },
157
+ "max_position_embeddings": 131072,
158
+ "model_type": "gemma4_vision",
159
+ "num_attention_heads": 12,
160
+ "num_hidden_layers": 16,
161
+ "num_key_value_heads": 12,
162
+ "output_attentions": false,
163
+ "output_hidden_states": false,
164
+ "patch_size": 16,
165
+ "pooling_kernel_size": 3,
166
+ "position_embedding_size": 10240,
167
+ "problem_type": null,
168
+ "return_dict": true,
169
+ "rms_norm_eps": 1e-06,
170
+ "rope_parameters": {
171
+ "rope_theta": 100.0,
172
+ "rope_type": "axial"
173
+ },
174
+ "standardize": false,
175
+ "use_clipped_linears": false
176
+ },
177
+ "vision_soft_tokens_per_image": 280
178
+ }