config.json
2.5 KB · 100 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 "bos_token_id": null,
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 "intermediate_size": 6144,
20 "layer_types": [
21 "linear_attention",
22 "linear_attention",
23 "linear_attention",
24 "full_attention",
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 ],
46 "linear_conv_kernel_dim": 4,
47 "linear_key_head_dim": 128,
48 "linear_num_key_heads": 16,
49 "linear_num_value_heads": 16,
50 "linear_value_head_dim": 128,
51 "mamba_ssm_dtype": "float32",
52 "max_position_embeddings": 262144,
53 "mlp_only_layers": [],
54 "model_type": "qwen3_5_text",
55 "mtp_num_hidden_layers": 1,
56 "mtp_use_dedicated_embeddings": false,
57 "num_attention_heads": 8,
58 "num_hidden_layers": 24,
59 "num_key_value_heads": 2,
60 "pad_token_id": null,
61 "partial_rotary_factor": 0.25,
62 "rms_norm_eps": 1e-06,
63 "rope_parameters": {
64 "mrope_interleaved": true,
65 "mrope_section": [
66 11,
67 11,
68 10
69 ],
70 "partial_rotary_factor": 0.25,
71 "rope_theta": 10000000,
72 "rope_type": "default"
73 },
74 "tie_word_embeddings": true,
75 "use_cache": true,
76 "vocab_size": 248320
77 },
78 "tie_word_embeddings": true,
79 "transformers_version": "5.2.0",
80 "video_token_id": 248057,
81 "vision_config": {
82 "deepstack_visual_indexes": [],
83 "depth": 24,
84 "hidden_act": "gelu_pytorch_tanh",
85 "hidden_size": 1024,
86 "in_channels": 3,
87 "initializer_range": 0.02,
88 "intermediate_size": 4096,
89 "model_type": "qwen3_5",
90 "num_heads": 16,
91 "num_position_embeddings": 2304,
92 "out_hidden_size": 2048,
93 "patch_size": 16,
94 "spatial_merge_size": 2,
95 "temporal_patch_size": 2
96 },
97 "vision_end_token_id": 248054,
98 "vision_start_token_id": 248053
99 }
100