config.json
3.2 KB · 127 lines · json Raw
1 {
2 "architectures": [
3 "Qwen3_5MoeForConditionalGeneration"
4 ],
5 "bos_token_id": null,
6 "dtype": "bfloat16",
7 "eos_token_id": 248046,
8 "hidden_size": 2048,
9 "image_token_id": 248056,
10 "model_type": "qwen3_5_moe",
11 "pad_token_id": 248044,
12 "text_config": {
13 "attention_bias": false,
14 "attention_dropout": 0.0,
15 "attn_output_gate": true,
16 "bos_token_id": 248044,
17 "dtype": "bfloat16",
18 "eos_token_id": 248044,
19 "full_attention_interval": 4,
20 "head_dim": 256,
21 "hidden_act": "silu",
22 "hidden_size": 2048,
23 "initializer_range": 0.02,
24 "layer_types": [
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 "linear_attention",
54 "linear_attention",
55 "linear_attention",
56 "full_attention",
57 "linear_attention",
58 "linear_attention",
59 "linear_attention",
60 "full_attention",
61 "linear_attention",
62 "linear_attention",
63 "linear_attention",
64 "full_attention"
65 ],
66 "linear_conv_kernel_dim": 4,
67 "linear_key_head_dim": 128,
68 "linear_num_key_heads": 16,
69 "linear_num_value_heads": 32,
70 "linear_value_head_dim": 128,
71 "mamba_ssm_dtype": "float32",
72 "max_position_embeddings": 262144,
73 "model_type": "qwen3_5_moe_text",
74 "moe_intermediate_size": 512,
75 "mtp_num_hidden_layers": 1,
76 "mtp_use_dedicated_embeddings": false,
77 "num_attention_heads": 16,
78 "num_experts": 256,
79 "num_experts_per_tok": 8,
80 "num_hidden_layers": 40,
81 "num_key_value_heads": 2,
82 "output_router_logits": false,
83 "pad_token_id": 248044,
84 "partial_rotary_factor": 0.25,
85 "rms_norm_eps": 1e-06,
86 "rope_parameters": {
87 "mrope_interleaved": true,
88 "mrope_section": [
89 11,
90 11,
91 10
92 ],
93 "partial_rotary_factor": 0.25,
94 "rope_theta": 10000000,
95 "rope_type": "default"
96 },
97 "router_aux_loss_coef": 0.0,
98 "shared_expert_intermediate_size": 512,
99 "tie_word_embeddings": false,
100 "use_cache": false,
101 "vocab_size": 248320
102 },
103 "tie_word_embeddings": false,
104 "transformers_version": "5.8.1",
105 "use_cache": false,
106 "video_token_id": 248057,
107 "vision_config": {
108 "deepstack_visual_indexes": [],
109 "depth": 27,
110 "dtype": "bfloat16",
111 "hidden_act": "gelu_pytorch_tanh",
112 "hidden_size": 1152,
113 "in_channels": 3,
114 "initializer_range": 0.02,
115 "intermediate_size": 4304,
116 "model_type": "qwen3_5_moe_vision",
117 "num_heads": 16,
118 "num_position_embeddings": 2304,
119 "out_hidden_size": 2048,
120 "patch_size": 16,
121 "spatial_merge_size": 2,
122 "temporal_patch_size": 2
123 },
124 "vision_end_token_id": 248054,
125 "vision_start_token_id": 248053
126 }
127