config.json
3.1 KB · 103 lines · json Raw
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 "dtype": "bfloat16",
12 "eos_token_id": 248044,
13 "full_attention_interval": 4,
14 "head_dim": 256,
15 "hidden_act": "silu",
16 "hidden_size": 4096,
17 "initializer_range": 0.02,
18 "intermediate_size": 12288,
19 "layer_types": [
20 "linear_attention",
21 "linear_attention",
22 "linear_attention",
23 "full_attention",
24 "linear_attention",
25 "linear_attention",
26 "linear_attention",
27 "full_attention",
28 "linear_attention",
29 "linear_attention",
30 "linear_attention",
31 "full_attention",
32 "linear_attention",
33 "linear_attention",
34 "linear_attention",
35 "full_attention",
36 "linear_attention",
37 "linear_attention",
38 "linear_attention",
39 "full_attention",
40 "linear_attention",
41 "linear_attention",
42 "linear_attention",
43 "full_attention",
44 "linear_attention",
45 "linear_attention",
46 "linear_attention",
47 "full_attention",
48 "linear_attention",
49 "linear_attention",
50 "linear_attention",
51 "full_attention"
52 ],
53 "linear_conv_kernel_dim": 4,
54 "linear_key_head_dim": 128,
55 "linear_num_key_heads": 16,
56 "linear_num_value_heads": 32,
57 "linear_value_head_dim": 128,
58 "max_position_embeddings": 262144,
59 "mlp_only_layers": [],
60 "model_type": "qwen3_5_text",
61 "mtp_num_hidden_layers": 1,
62 "mtp_use_dedicated_embeddings": false,
63 "num_attention_heads": 16,
64 "num_hidden_layers": 32,
65 "num_key_value_heads": 4,
66 "rms_norm_eps": 1e-06,
67 "use_cache": true,
68 "vocab_size": 248320,
69 "mamba_ssm_dtype": "float32",
70 "rope_parameters": {
71 "mrope_interleaved": true,
72 "mrope_section": [
73 11,
74 11,
75 10
76 ],
77 "rope_type": "default",
78 "rope_theta": 10000000,
79 "partial_rotary_factor": 0.25
80 }
81 },
82 "tie_word_embeddings": false,
83 "transformers_version": "4.57.0.dev0",
84 "video_token_id": 248057,
85 "vision_config": {
86 "deepstack_visual_indexes": [],
87 "depth": 27,
88 "hidden_act": "gelu_pytorch_tanh",
89 "hidden_size": 1152,
90 "in_channels": 3,
91 "initializer_range": 0.02,
92 "intermediate_size": 4304,
93 "model_type": "qwen3_5",
94 "num_heads": 16,
95 "num_position_embeddings": 2304,
96 "out_hidden_size": 4096,
97 "patch_size": 16,
98 "spatial_merge_size": 2,
99 "temporal_patch_size": 2
100 },
101 "vision_end_token_id": 248054,
102 "vision_start_token_id": 248053
103 }