config.json
3.6 KB · 119 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 "bos_token_id": 248044,
12 "dtype": "bfloat16",
13 "eos_token_id": 248044,
14 "full_attention_interval": 4,
15 "head_dim": 256,
16 "hidden_act": "silu",
17 "hidden_size": 2048,
18 "initializer_range": 0.02,
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 "linear_attention",
53 "linear_attention",
54 "linear_attention",
55 "full_attention",
56 "linear_attention",
57 "linear_attention",
58 "linear_attention",
59 "full_attention"
60 ],
61 "linear_conv_kernel_dim": 4,
62 "linear_key_head_dim": 128,
63 "linear_num_key_heads": 16,
64 "linear_num_value_heads": 32,
65 "linear_value_head_dim": 128,
66 "mamba_ssm_dtype": "float32",
67 "max_position_embeddings": 262144,
68 "model_type": "qwen3_5_moe_text",
69 "moe_intermediate_size": 512,
70 "mtp_num_hidden_layers": 1,
71 "mtp_use_dedicated_embeddings": false,
72 "num_attention_heads": 16,
73 "num_experts": 256,
74 "num_experts_per_tok": 8,
75 "num_hidden_layers": 40,
76 "num_key_value_heads": 2,
77 "output_router_logits": false,
78 "pad_token_id": null,
79 "partial_rotary_factor": 0.25,
80 "rms_norm_eps": 1e-06,
81 "rope_parameters": {
82 "mrope_interleaved": true,
83 "mrope_section": [
84 11,
85 11,
86 10
87 ],
88 "partial_rotary_factor": 0.25,
89 "rope_theta": 10000000,
90 "rope_type": "default"
91 },
92 "router_aux_loss_coef": 0.001,
93 "shared_expert_intermediate_size": 512,
94 "tie_word_embeddings": false,
95 "use_cache": true,
96 "vocab_size": 248320
97 },
98 "tie_word_embeddings": false,
99 "transformers_version": "4.57.1",
100 "video_token_id": 248057,
101 "vision_config": {
102 "deepstack_visual_indexes": [],
103 "depth": 27,
104 "hidden_act": "gelu_pytorch_tanh",
105 "hidden_size": 1152,
106 "in_channels": 3,
107 "initializer_range": 0.02,
108 "intermediate_size": 4304,
109 "model_type": "qwen3_5_moe",
110 "num_heads": 16,
111 "num_position_embeddings": 2304,
112 "out_hidden_size": 2048,
113 "patch_size": 16,
114 "spatial_merge_size": 2,
115 "temporal_patch_size": 2
116 },
117 "vision_end_token_id": 248054,
118 "vision_start_token_id": 248053
119 }