louis030195 commited on
Commit
86fc6fc
·
verified ·
1 Parent(s): 324d052

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +109 -0
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "model_type": "qwen3_5",
8
+ "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_output_gate": true,
12
+ "bos_token_id": null,
13
+ "dtype": "bfloat16",
14
+ "eos_token_id": 248044,
15
+ "full_attention_interval": 4,
16
+ "head_dim": 256,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 4096,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 12288,
21
+ "layer_types": [
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention"
54
+ ],
55
+ "linear_conv_kernel_dim": 4,
56
+ "linear_key_head_dim": 128,
57
+ "linear_num_key_heads": 16,
58
+ "linear_num_value_heads": 32,
59
+ "linear_value_head_dim": 128,
60
+ "mamba_ssm_dtype": "float32",
61
+ "max_position_embeddings": 262144,
62
+ "mlp_only_layers": [],
63
+ "model_type": "qwen3_5_text",
64
+ "mtp_num_hidden_layers": 1,
65
+ "mtp_use_dedicated_embeddings": false,
66
+ "num_attention_heads": 16,
67
+ "num_hidden_layers": 32,
68
+ "num_key_value_heads": 4,
69
+ "pad_token_id": null,
70
+ "partial_rotary_factor": 0.25,
71
+ "rms_norm_eps": 1e-06,
72
+ "rope_parameters": {
73
+ "mrope_interleaved": true,
74
+ "mrope_section": [
75
+ 11,
76
+ 11,
77
+ 10
78
+ ],
79
+ "partial_rotary_factor": 0.25,
80
+ "rope_theta": 10000000,
81
+ "rope_type": "default"
82
+ },
83
+ "tie_word_embeddings": false,
84
+ "use_cache": true,
85
+ "vocab_size": 248320
86
+ },
87
+ "tie_word_embeddings": false,
88
+ "transformers_version": "5.5.0.dev0",
89
+ "video_token_id": 248057,
90
+ "vision_config": {
91
+ "deepstack_visual_indexes": [],
92
+ "depth": 27,
93
+ "dtype": "bfloat16",
94
+ "hidden_act": "gelu_pytorch_tanh",
95
+ "hidden_size": 1152,
96
+ "in_channels": 3,
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 4304,
99
+ "model_type": "qwen3_5",
100
+ "num_heads": 16,
101
+ "num_position_embeddings": 2304,
102
+ "out_hidden_size": 4096,
103
+ "patch_size": 16,
104
+ "spatial_merge_size": 2,
105
+ "temporal_patch_size": 2
106
+ },
107
+ "vision_end_token_id": 248054,
108
+ "vision_start_token_id": 248053
109
+ }