Update config.json
Browse files- config.json +31 -186
config.json
CHANGED
@@ -1,190 +1,35 @@
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
-
"WednesdayModel"
|
4 |
-
"Gemma3nForConditionalGeneration"
|
5 |
],
|
6 |
-
"
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
"conf_attention_logit_cap": 50.0,
|
11 |
-
"conf_conv_kernel_size": 5,
|
12 |
-
"conf_num_attention_heads": 8,
|
13 |
-
"conf_num_hidden_layers": 12,
|
14 |
-
"conf_positional_bias_size": 256,
|
15 |
-
"conf_reduction_factor": 4,
|
16 |
-
"conf_residual_weight": 0.5,
|
17 |
-
"gradient_clipping": 10000000000.0,
|
18 |
-
"hidden_size": 1536,
|
19 |
-
"input_feat_size": 128,
|
20 |
-
"model_type": "gemma3n_audio",
|
21 |
-
"rms_norm_eps": 1e-06,
|
22 |
-
"sscp_conv_channel_size": [
|
23 |
-
128,
|
24 |
-
32
|
25 |
-
],
|
26 |
-
"sscp_conv_eps": 0.001,
|
27 |
-
"sscp_conv_kernel_size": [
|
28 |
-
[
|
29 |
-
3,
|
30 |
-
3
|
31 |
-
],
|
32 |
-
[
|
33 |
-
3,
|
34 |
-
3
|
35 |
-
]
|
36 |
-
],
|
37 |
-
"sscp_conv_stride_size": [
|
38 |
-
[
|
39 |
-
2,
|
40 |
-
2
|
41 |
-
],
|
42 |
-
[
|
43 |
-
2,
|
44 |
-
2
|
45 |
-
]
|
46 |
-
],
|
47 |
-
"torch_dtype": "bfloat16",
|
48 |
-
"vocab_offset": 262272,
|
49 |
-
"vocab_size": 128
|
50 |
-
},
|
51 |
-
"audio_soft_tokens_per_image": 188,
|
52 |
-
"audio_token_id": 262273,
|
53 |
-
"boa_token_id": 256000,
|
54 |
-
"boi_token_id": 255999,
|
55 |
-
"eoa_token_id": 262272,
|
56 |
-
"eoi_token_id": 262144,
|
57 |
-
"image_token_id": 262145,
|
58 |
"initializer_range": 0.02,
|
59 |
-
"
|
60 |
-
"
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
0.0,
|
86 |
-
0.0,
|
87 |
-
0.0,
|
88 |
-
0.0,
|
89 |
-
0.0,
|
90 |
-
0.0,
|
91 |
-
0.0
|
92 |
-
],
|
93 |
-
"altup_active_idx": 0,
|
94 |
-
"altup_coef_clip": 120.0,
|
95 |
-
"altup_correct_scale": true,
|
96 |
-
"altup_lr_multiplier": 1.0,
|
97 |
-
"altup_num_inputs": 4,
|
98 |
-
"attention_bias": false,
|
99 |
-
"attention_dropout": 0.0,
|
100 |
-
"final_logit_softcapping": 30.0,
|
101 |
-
"head_dim": 256,
|
102 |
-
"hidden_activation": "gelu_pytorch_tanh",
|
103 |
-
"hidden_size": 2048,
|
104 |
-
"hidden_size_per_layer_input": 256,
|
105 |
-
"initializer_range": 0.02,
|
106 |
-
"intermediate_size": 8192,
|
107 |
-
"laurel_rank": 64,
|
108 |
-
"layer_types": [
|
109 |
-
"sliding_attention",
|
110 |
-
"sliding_attention",
|
111 |
-
"sliding_attention",
|
112 |
-
"sliding_attention",
|
113 |
-
"full_attention",
|
114 |
-
"sliding_attention",
|
115 |
-
"sliding_attention",
|
116 |
-
"sliding_attention",
|
117 |
-
"sliding_attention",
|
118 |
-
"full_attention",
|
119 |
-
"sliding_attention",
|
120 |
-
"sliding_attention",
|
121 |
-
"sliding_attention",
|
122 |
-
"sliding_attention",
|
123 |
-
"full_attention",
|
124 |
-
"sliding_attention",
|
125 |
-
"sliding_attention",
|
126 |
-
"sliding_attention",
|
127 |
-
"sliding_attention",
|
128 |
-
"full_attention",
|
129 |
-
"sliding_attention",
|
130 |
-
"sliding_attention",
|
131 |
-
"sliding_attention",
|
132 |
-
"sliding_attention",
|
133 |
-
"full_attention",
|
134 |
-
"sliding_attention",
|
135 |
-
"sliding_attention",
|
136 |
-
"sliding_attention",
|
137 |
-
"sliding_attention",
|
138 |
-
"full_attention"
|
139 |
-
],
|
140 |
-
"bos_token_id": 1,
|
141 |
-
"eos_token_id": 2,
|
142 |
-
"hidden_act": "gelu_pytorch_tanh",
|
143 |
-
"hidden_size": 768,
|
144 |
-
"initializer_range": 0.02,
|
145 |
-
"intermediate_size": 3072,
|
146 |
-
"max_position_embeddings": 32768,
|
147 |
-
"model_type": "gemma3n_text",
|
148 |
-
"moe_2layer_gate": true,
|
149 |
-
"moe_expert_interval": 1,
|
150 |
-
"moe_feature_no_mul_topk": true,
|
151 |
-
"moe_gate_norm_std": 1.0,
|
152 |
-
"moe_use_logits_norm": true,
|
153 |
-
"moe_use_mixtral_gating": true,
|
154 |
-
"num_attention_heads": 12,
|
155 |
-
"num_experts": [
|
156 |
-
8
|
157 |
-
],
|
158 |
-
"num_hidden_layers": 4,
|
159 |
-
"num_key_value_heads": 2,
|
160 |
-
"pad_token_id": 0,
|
161 |
-
"pretraining_tp": 1,
|
162 |
-
"rms_norm_eps": 1e-06,
|
163 |
-
"rope_scaling": null,
|
164 |
-
"rope_theta": 1000000.0,
|
165 |
-
"tie_word_embeddings": false,
|
166 |
-
"torch_dtype": "float32",
|
167 |
-
"transformers_version": "4.53.1",
|
168 |
-
"use_cache": true,
|
169 |
-
"vocab_size": 262400
|
170 |
-
},
|
171 |
-
"torch_dtype": "bfloat16",
|
172 |
-
"transformers_version": "4.53.0.dev0",
|
173 |
-
"vision_config": {
|
174 |
-
"architecture": "mobilenetv5_300m_enc",
|
175 |
-
"do_pooling": true,
|
176 |
-
"hidden_size": 2048,
|
177 |
-
"initializer_range": 0.02,
|
178 |
-
"label_names": [
|
179 |
-
"LABEL_0",
|
180 |
-
"LABEL_1"
|
181 |
-
],
|
182 |
-
"model_type": "gemma3n_vision",
|
183 |
-
"num_classes": 2,
|
184 |
-
"rms_norm_eps": 1e-06,
|
185 |
-
"torch_dtype": "bfloat16",
|
186 |
-
"vocab_offset": 262144,
|
187 |
-
"vocab_size": 128
|
188 |
-
},
|
189 |
-
"vision_soft_tokens_per_image": 256
|
190 |
-
}
|
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
+
"WednesdayModel"
|
|
|
4 |
],
|
5 |
+
"bos_token_id": 1,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "gelu_pytorch_tanh",
|
8 |
+
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 3072,
|
11 |
+
"max_position_embeddings": 32768,
|
12 |
+
"model_type": "MoE++",
|
13 |
+
"moe_2layer_gate": true,
|
14 |
+
"moe_expert_interval": 1,
|
15 |
+
"moe_feature_no_mul_topk": true,
|
16 |
+
"moe_gate_norm_std": 1.0,
|
17 |
+
"moe_use_logits_norm": true,
|
18 |
+
"moe_use_mixtral_gating": true,
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_experts": [
|
21 |
+
8
|
22 |
+
],
|
23 |
+
"num_hidden_layers": 4,
|
24 |
+
"num_key_value_heads": 2,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-06,
|
28 |
+
"rope_scaling": null,
|
29 |
+
"rope_theta": 1000000.0,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.53.1",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 262400
|
35 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|