Hugging Face's logo

compiledcode83
/
consider_mDK2RD

qwen3_5_moe
Model card Files
xet
 Community
compiledcode83 commited on
Commit
fc7d124
·
verified ·
1 Parent(s): 644f5d1

probe upload

Browse files
Files changed (1) hide show
  1. config.json +168 -0
config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "transformers_version": "5.12.1",
3
+ "architectures": [
4
+ "Qwen3_5MoeForConditionalGeneration"
5
+ ],
6
+ "output_hidden_states": false,
7
+ "return_dict": true,
8
+ "dtype": null,
9
+ "chunk_size_feed_forward": 0,
10
+ "is_encoder_decoder": false,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1"
14
+ },
15
+ "label2id": {
16
+ "LABEL_0": 0,
17
+ "LABEL_1": 1
18
+ },
19
+ "problem_type": null,
20
+ "text_config": {
21
+ "architectures": null,
22
+ "output_hidden_states": false,
23
+ "return_dict": true,
24
+ "dtype": "bfloat16",
25
+ "chunk_size_feed_forward": 0,
26
+ "is_encoder_decoder": false,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1
34
+ },
35
+ "problem_type": null,
36
+ "vocab_size": 248320,
37
+ "hidden_size": 2048,
38
+ "num_hidden_layers": 40,
39
+ "num_attention_heads": 16,
40
+ "num_key_value_heads": 2,
41
+ "hidden_act": "silu",
42
+ "max_position_embeddings": 262144,
43
+ "initializer_range": 0.02,
44
+ "rms_norm_eps": 1e-06,
45
+ "use_cache": false,
46
+ "tie_word_embeddings": false,
47
+ "rope_parameters": {
48
+ "mrope_interleaved": true,
49
+ "mrope_section": [
50
+ 11,
51
+ 11,
52
+ 10
53
+ ],
54
+ "partial_rotary_factor": 0.25,
55
+ "rope_theta": 10000000,
56
+ "rope_type": "default"
57
+ },
58
+ "attention_bias": false,
59
+ "attention_dropout": 0.0,
60
+ "head_dim": 256,
61
+ "linear_conv_kernel_dim": 4,
62
+ "linear_key_head_dim": 128,
63
+ "linear_value_head_dim": 128,
64
+ "linear_num_key_heads": 16,
65
+ "linear_num_value_heads": 32,
66
+ "moe_intermediate_size": 512,
67
+ "shared_expert_intermediate_size": 512,
68
+ "num_experts_per_tok": 8,
69
+ "num_experts": 256,
70
+ "output_router_logits": false,
71
+ "router_aux_loss_coef": 0.001,
72
+ "layer_types": [
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "full_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "full_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "full_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "full_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "linear_attention",
92
+ "full_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "linear_attention",
96
+ "full_attention",
97
+ "linear_attention",
98
+ "linear_attention",
99
+ "linear_attention",
100
+ "full_attention",
101
+ "linear_attention",
102
+ "linear_attention",
103
+ "linear_attention",
104
+ "full_attention",
105
+ "linear_attention",
106
+ "linear_attention",
107
+ "linear_attention",
108
+ "full_attention",
109
+ "linear_attention",
110
+ "linear_attention",
111
+ "linear_attention",
112
+ "full_attention"
113
+ ],
114
+ "pad_token_id": 248044,
115
+ "bos_token_id": null,
116
+ "eos_token_id": 248046,
117
+ "_name_or_path": "",
118
+ "attn_output_gate": true,
119
+ "full_attention_interval": 4,
120
+ "mamba_ssm_dtype": "float32",
121
+ "model_type": "qwen3_5_moe_text",
122
+ "mtp_num_hidden_layers": 1,
123
+ "mtp_use_dedicated_embeddings": false,
124
+ "partial_rotary_factor": 0.25,
125
+ "output_attentions": false
126
+ },
127
+ "vision_config": {
128
+ "architectures": null,
129
+ "output_hidden_states": false,
130
+ "return_dict": true,
131
+ "dtype": null,
132
+ "chunk_size_feed_forward": 0,
133
+ "is_encoder_decoder": false,
134
+ "id2label": {
135
+ "0": "LABEL_0",
136
+ "1": "LABEL_1"
137
+ },
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "problem_type": null,
143
+ "depth": 27,
144
+ "hidden_size": 1152,
145
+ "hidden_act": "gelu_pytorch_tanh",
146
+ "intermediate_size": 4304,
147
+ "num_heads": 16,
148
+ "in_channels": 3,
149
+ "patch_size": 16,
150
+ "spatial_merge_size": 2,
151
+ "temporal_patch_size": 2,
152
+ "out_hidden_size": 2048,
153
+ "num_position_embeddings": 2304,
154
+ "initializer_range": 0.02,
155
+ "_name_or_path": "",
156
+ "deepstack_visual_indexes": [],
157
+ "model_type": "qwen3_5_moe_vision",
158
+ "output_attentions": false
159
+ },
160
+ "image_token_id": 248056,
161
+ "video_token_id": 248057,
162
+ "vision_start_token_id": 248053,
163
+ "vision_end_token_id": 248054,
164
+ "tie_word_embeddings": false,
165
+ "model_type": "qwen3_5_moe",
166
+ "output_attentions": false,
167
+ "torch_dtype": "bfloat16"
168
+ }