config.json
2.8 KB · 96 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": 1024,
17 "initializer_range": 0.02,
18 "intermediate_size": 3584,
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 ],
45 "linear_conv_kernel_dim": 4,
46 "linear_key_head_dim": 128,
47 "linear_num_key_heads": 16,
48 "linear_num_value_heads": 16,
49 "linear_value_head_dim": 128,
50 "max_position_embeddings": 262144,
51 "mlp_only_layers": [],
52 "model_type": "qwen3_5_text",
53 "mtp_num_hidden_layers": 1,
54 "mtp_use_dedicated_embeddings": false,
55 "num_attention_heads": 8,
56 "num_hidden_layers": 24,
57 "num_key_value_heads": 2,
58 "rms_norm_eps": 1e-06,
59 "tie_word_embeddings": true,
60 "use_cache": true,
61 "vocab_size": 248320,
62 "mamba_ssm_dtype": "float32",
63 "rope_parameters": {
64 "mrope_interleaved": true,
65 "mrope_section": [
66 11,
67 11,
68 10
69 ],
70 "rope_type": "default",
71 "rope_theta": 10000000,
72 "partial_rotary_factor": 0.25
73 }
74 },
75 "tie_word_embeddings": true,
76 "transformers_version": "4.57.0.dev0",
77 "video_token_id": 248057,
78 "vision_config": {
79 "deepstack_visual_indexes": [],
80 "depth": 12,
81 "hidden_act": "gelu_pytorch_tanh",
82 "hidden_size": 768,
83 "in_channels": 3,
84 "initializer_range": 0.02,
85 "intermediate_size": 3072,
86 "model_type": "qwen3_5",
87 "num_heads": 12,
88 "num_position_embeddings": 2304,
89 "out_hidden_size": 1024,
90 "patch_size": 16,
91 "spatial_merge_size": 2,
92 "temporal_patch_size": 2
93 },
94 "vision_end_token_id": 248054,
95 "vision_start_token_id": 248053
96 }