config.json
3.5 KB · 115 lines · json Raw
1 {
2 "architectures": [
3 "Qwen3_5MoeForConditionalGeneration"
4 ],
5 "image_token_id": 248056,
6 "model_type": "qwen3_5_moe",
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": 2048,
17 "initializer_range": 0.02,
18 "layer_types": [
19 "linear_attention",
20 "linear_attention",
21 "linear_attention",
22 "full_attention",
23 "linear_attention",
24 "linear_attention",
25 "linear_attention",
26 "full_attention",
27 "linear_attention",
28 "linear_attention",
29 "linear_attention",
30 "full_attention",
31 "linear_attention",
32 "linear_attention",
33 "linear_attention",
34 "full_attention",
35 "linear_attention",
36 "linear_attention",
37 "linear_attention",
38 "full_attention",
39 "linear_attention",
40 "linear_attention",
41 "linear_attention",
42 "full_attention",
43 "linear_attention",
44 "linear_attention",
45 "linear_attention",
46 "full_attention",
47 "linear_attention",
48 "linear_attention",
49 "linear_attention",
50 "full_attention",
51 "linear_attention",
52 "linear_attention",
53 "linear_attention",
54 "full_attention",
55 "linear_attention",
56 "linear_attention",
57 "linear_attention",
58 "full_attention"
59 ],
60 "linear_conv_kernel_dim": 4,
61 "linear_key_head_dim": 128,
62 "linear_num_key_heads": 16,
63 "linear_num_value_heads": 32,
64 "linear_value_head_dim": 128,
65 "max_position_embeddings": 262144,
66 "mlp_only_layers": [],
67 "model_type": "qwen3_5_moe_text",
68 "moe_intermediate_size": 512,
69 "mtp_num_hidden_layers": 1,
70 "mtp_use_dedicated_embeddings": false,
71 "num_attention_heads": 16,
72 "num_experts": 256,
73 "num_experts_per_tok": 8,
74 "num_hidden_layers": 40,
75 "num_key_value_heads": 2,
76 "rms_norm_eps": 1e-06,
77 "router_aux_loss_coef": 0.001,
78 "shared_expert_intermediate_size": 512,
79 "use_cache": true,
80 "vocab_size": 248320,
81 "mamba_ssm_dtype": "float32",
82 "rope_parameters": {
83 "mrope_interleaved": true,
84 "mrope_section": [
85 11,
86 11,
87 10
88 ],
89 "rope_type": "default",
90 "rope_theta": 10000000,
91 "partial_rotary_factor": 0.25
92 }
93 },
94 "tie_word_embeddings": false,
95 "transformers_version": "4.57.0.dev0",
96 "video_token_id": 248057,
97 "vision_config": {
98 "deepstack_visual_indexes": [],
99 "depth": 27,
100 "hidden_act": "gelu_pytorch_tanh",
101 "hidden_size": 1152,
102 "in_channels": 3,
103 "initializer_range": 0.02,
104 "intermediate_size": 4304,
105 "model_type": "qwen3_5_moe",
106 "num_heads": 16,
107 "num_position_embeddings": 2304,
108 "out_hidden_size": 2048,
109 "patch_size": 16,
110 "spatial_merge_size": 2,
111 "temporal_patch_size": 2
112 },
113 "vision_end_token_id": 248054,
114 "vision_start_token_id": 248053
115 }