OliviaRossi commited on
Commit
a255a7b
·
verified ·
1 Parent(s): 12b5bfe

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
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "bos_token_id": null,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "full_attention_interval": 4,
15
+ "head_dim": 256,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 4096,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 12288,
20
+ "layer_types": [
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "full_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention"
53
+ ],
54
+ "linear_conv_kernel_dim": 4,
55
+ "linear_key_head_dim": 128,
56
+ "linear_num_key_heads": 16,
57
+ "linear_num_value_heads": 32,
58
+ "linear_value_head_dim": 128,
59
+ "mamba_ssm_dtype": "float32",
60
+ "max_position_embeddings": 262144,
61
+ "mlp_only_layers": [],
62
+ "model_type": "qwen3_5_text",
63
+ "mtp_num_hidden_layers": 1,
64
+ "mtp_use_dedicated_embeddings": false,
65
+ "num_attention_heads": 16,
66
+ "num_hidden_layers": 32,
67
+ "num_key_value_heads": 4,
68
+ "pad_token_id": null,
69
+ "partial_rotary_factor": 0.25,
70
+ "rms_norm_eps": 1e-06,
71
+ "rope_parameters": {
72
+ "mrope_interleaved": true,
73
+ "mrope_section": [
74
+ 11,
75
+ 11,
76
+ 10
77
+ ],
78
+ "partial_rotary_factor": 0.25,
79
+ "rope_theta": 10000000,
80
+ "rope_type": "default"
81
+ },
82
+ "tie_word_embeddings": false,
83
+ "use_cache": true,
84
+ "vocab_size": 248320
85
+ },
86
+ "tie_word_embeddings": false,
87
+ "transformers_version": "5.12.1",
88
+ "video_token_id": 248057,
89
+ "vision_config": {
90
+ "deepstack_visual_indexes": [],
91
+ "depth": 27,
92
+ "hidden_act": "gelu_pytorch_tanh",
93
+ "hidden_size": 1152,
94
+ "in_channels": 3,
95
+ "initializer_range": 0.02,
96
+ "intermediate_size": 4304,
97
+ "model_type": "qwen3_5_vision",
98
+ "num_heads": 16,
99
+ "num_position_embeddings": 2304,
100
+ "out_hidden_size": 4096,
101
+ "patch_size": 16,
102
+ "spatial_merge_size": 2,
103
+ "temporal_patch_size": 2
104
+ },
105
+ "vision_end_token_id": 248054,
106
+ "vision_start_token_id": 248053,
107
+ "_name_or_path": "OliviaRossi/MiMo-Negentropy-9B-AGSI",
108
+ "torch_dtype": "bfloat16"
109
+ }