config.json
1.4 KB · 63 lines · json Raw
1 {
2 "architectures": [
3 "Qwen3VLForConditionalGeneration"
4 ],
5 "image_token_id": 151655,
6 "model_type": "qwen3_vl",
7 "text_config": {
8 "attention_bias": false,
9 "attention_dropout": 0.0,
10 "bos_token_id": 151643,
11 "dtype": "bfloat16",
12 "eos_token_id": 151645,
13 "head_dim": 128,
14 "hidden_act": "silu",
15 "hidden_size": 4096,
16 "initializer_range": 0.02,
17 "intermediate_size": 12288,
18 "max_position_embeddings": 262144,
19 "model_type": "qwen3_vl_text",
20 "num_attention_heads": 32,
21 "num_hidden_layers": 36,
22 "num_key_value_heads": 8,
23 "rms_norm_eps": 1e-06,
24 "rope_scaling": {
25 "mrope_interleaved": true,
26 "mrope_section": [
27 24,
28 20,
29 20
30 ],
31 "rope_type": "default"
32 },
33 "rope_theta": 5000000,
34 "use_cache": true,
35 "vocab_size": 151936
36 },
37 "tie_word_embeddings": false,
38 "transformers_version": "4.57.0.dev0",
39 "video_token_id": 151656,
40 "vision_config": {
41 "deepstack_visual_indexes": [
42 8,
43 16,
44 24
45 ],
46 "depth": 27,
47 "hidden_act": "gelu_pytorch_tanh",
48 "hidden_size": 1152,
49 "in_channels": 3,
50 "initializer_range": 0.02,
51 "intermediate_size": 4304,
52 "model_type": "qwen3_vl",
53 "num_heads": 16,
54 "num_position_embeddings": 2304,
55 "out_hidden_size": 4096,
56 "patch_size": 16,
57 "spatial_merge_size": 2,
58 "temporal_patch_size": 2
59 },
60 "vision_end_token_id": 151653,
61 "vision_start_token_id": 151652
62 }
63