Update config.json
Browse files- config.json +159 -1
config.json
CHANGED
@@ -2,6 +2,144 @@
|
|
2 |
"architectures": [
|
3 |
"WednesdayModel"
|
4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"bos_token_id": 1,
|
6 |
"eos_token_id": 2,
|
7 |
"hidden_act": "gelu_pytorch_tanh",
|
@@ -9,7 +147,7 @@
|
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 3072,
|
11 |
"max_position_embeddings": 32768,
|
12 |
-
"model_type": "
|
13 |
"moe_2layer_gate": true,
|
14 |
"moe_expert_interval": 1,
|
15 |
"moe_feature_no_mul_topk": true,
|
@@ -33,3 +171,23 @@
|
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 262400
|
35 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"architectures": [
|
3 |
"WednesdayModel"
|
4 |
],
|
5 |
+
{
|
6 |
+
"architectures": [
|
7 |
+
"Gemma3nForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"audio_config": {
|
10 |
+
"conf_attention_chunk_size": 12,
|
11 |
+
"conf_attention_context_left": 13,
|
12 |
+
"conf_attention_context_right": 0,
|
13 |
+
"conf_attention_logit_cap": 50.0,
|
14 |
+
"conf_conv_kernel_size": 5,
|
15 |
+
"conf_num_attention_heads": 8,
|
16 |
+
"conf_num_hidden_layers": 12,
|
17 |
+
"conf_positional_bias_size": 256,
|
18 |
+
"conf_reduction_factor": 4,
|
19 |
+
"conf_residual_weight": 0.5,
|
20 |
+
"gradient_clipping": 10000000000.0,
|
21 |
+
"hidden_size": 1536,
|
22 |
+
"input_feat_size": 128,
|
23 |
+
"model_type": "gemma3n_audio",
|
24 |
+
"rms_norm_eps": 1e-06,
|
25 |
+
"sscp_conv_channel_size": [
|
26 |
+
128,
|
27 |
+
32
|
28 |
+
],
|
29 |
+
"sscp_conv_eps": 0.001,
|
30 |
+
"sscp_conv_kernel_size": [
|
31 |
+
[
|
32 |
+
3,
|
33 |
+
3
|
34 |
+
],
|
35 |
+
[
|
36 |
+
3,
|
37 |
+
3
|
38 |
+
]
|
39 |
+
],
|
40 |
+
"sscp_conv_stride_size": [
|
41 |
+
[
|
42 |
+
2,
|
43 |
+
2
|
44 |
+
],
|
45 |
+
[
|
46 |
+
2,
|
47 |
+
2
|
48 |
+
]
|
49 |
+
],
|
50 |
+
"torch_dtype": "bfloat16",
|
51 |
+
"vocab_offset": 262272,
|
52 |
+
"vocab_size": 128
|
53 |
+
},
|
54 |
+
"audio_soft_tokens_per_image": 188,
|
55 |
+
"audio_token_id": 262273,
|
56 |
+
"boa_token_id": 256000,
|
57 |
+
"boi_token_id": 255999,
|
58 |
+
"eoa_token_id": 262272,
|
59 |
+
"eoi_token_id": 262144,
|
60 |
+
"image_token_id": 262145,
|
61 |
+
"initializer_range": 0.02,
|
62 |
+
"model_type": "gemma3n",
|
63 |
+
"text_config": {
|
64 |
+
"activation_sparsity_pattern": [
|
65 |
+
0.95,
|
66 |
+
0.95,
|
67 |
+
0.95,
|
68 |
+
0.95,
|
69 |
+
0.95,
|
70 |
+
0.95,
|
71 |
+
0.95,
|
72 |
+
0.95,
|
73 |
+
0.95,
|
74 |
+
0.95,
|
75 |
+
0.0,
|
76 |
+
0.0,
|
77 |
+
0.0,
|
78 |
+
0.0,
|
79 |
+
0.0,
|
80 |
+
0.0,
|
81 |
+
0.0,
|
82 |
+
0.0,
|
83 |
+
0.0,
|
84 |
+
0.0,
|
85 |
+
0.0,
|
86 |
+
0.0,
|
87 |
+
0.0,
|
88 |
+
0.0,
|
89 |
+
0.0,
|
90 |
+
0.0,
|
91 |
+
0.0,
|
92 |
+
0.0,
|
93 |
+
0.0,
|
94 |
+
0.0
|
95 |
+
],
|
96 |
+
"altup_active_idx": 0,
|
97 |
+
"altup_coef_clip": 120.0,
|
98 |
+
"altup_correct_scale": true,
|
99 |
+
"altup_lr_multiplier": 1.0,
|
100 |
+
"altup_num_inputs": 4,
|
101 |
+
"attention_bias": false,
|
102 |
+
"attention_dropout": 0.0,
|
103 |
+
"final_logit_softcapping": 30.0,
|
104 |
+
"head_dim": 256,
|
105 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
106 |
+
"hidden_size": 2048,
|
107 |
+
"hidden_size_per_layer_input": 256,
|
108 |
+
"initializer_range": 0.02,
|
109 |
+
"intermediate_size": 8192,
|
110 |
+
"laurel_rank": 64,
|
111 |
+
"layer_types": [
|
112 |
+
"sliding_attention",
|
113 |
+
"sliding_attention",
|
114 |
+
"sliding_attention",
|
115 |
+
"sliding_attention",
|
116 |
+
"full_attention",
|
117 |
+
"sliding_attention",
|
118 |
+
"sliding_attention",
|
119 |
+
"sliding_attention",
|
120 |
+
"sliding_attention",
|
121 |
+
"full_attention",
|
122 |
+
"sliding_attention",
|
123 |
+
"sliding_attention",
|
124 |
+
"sliding_attention",
|
125 |
+
"sliding_attention",
|
126 |
+
"full_attention",
|
127 |
+
"sliding_attention",
|
128 |
+
"sliding_attention",
|
129 |
+
"sliding_attention",
|
130 |
+
"sliding_attention",
|
131 |
+
"full_attention",
|
132 |
+
"sliding_attention",
|
133 |
+
"sliding_attention",
|
134 |
+
"sliding_attention",
|
135 |
+
"sliding_attention",
|
136 |
+
"full_attention",
|
137 |
+
"sliding_attention",
|
138 |
+
"sliding_attention",
|
139 |
+
"sliding_attention",
|
140 |
+
"sliding_attention",
|
141 |
+
"full_attention"
|
142 |
+
],
|
143 |
"bos_token_id": 1,
|
144 |
"eos_token_id": 2,
|
145 |
"hidden_act": "gelu_pytorch_tanh",
|
|
|
147 |
"initializer_range": 0.02,
|
148 |
"intermediate_size": 3072,
|
149 |
"max_position_embeddings": 32768,
|
150 |
+
"model_type": "gemma3n_text",
|
151 |
"moe_2layer_gate": true,
|
152 |
"moe_expert_interval": 1,
|
153 |
"moe_feature_no_mul_topk": true,
|
|
|
171 |
"use_cache": true,
|
172 |
"vocab_size": 262400
|
173 |
}
|
174 |
+
"torch_dtype": "bfloat16",
|
175 |
+
"transformers_version": "4.53.0.dev0",
|
176 |
+
"vision_config": {
|
177 |
+
"architecture": "mobilenetv5_300m_enc",
|
178 |
+
"do_pooling": true,
|
179 |
+
"hidden_size": 2048,
|
180 |
+
"initializer_range": 0.02,
|
181 |
+
"label_names": [
|
182 |
+
"LABEL_0",
|
183 |
+
"LABEL_1"
|
184 |
+
],
|
185 |
+
"model_type": "gemma3n_vision",
|
186 |
+
"num_classes": 2,
|
187 |
+
"rms_norm_eps": 1e-06,
|
188 |
+
"torch_dtype": "bfloat16",
|
189 |
+
"vocab_offset": 262144,
|
190 |
+
"vocab_size": 128
|
191 |
+
},
|
192 |
+
"vision_soft_tokens_per_image": 256
|
193 |
+
}
|