zen-omni/config.json at main · zenlm/zen-omni · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
{
  "_name_or_path": "Qwen3-Omni",
  "architectures": [
    "Qwen3OmniForConditionalGeneration"
  ],
  "base_model": "Qwen3-Omni",
  "model_type": "zen-omni",
  "multimodal": true,
  "supported_modalities": ["text", "image", "audio"],
  "vocab_size": 151936,
  "hidden_size": 3584,
  "intermediate_size": 18944,
  "num_hidden_layers": 28,
  "num_attention_heads": 28,
  "num_key_value_heads": 4,
  "hidden_act": "silu",
  "max_position_embeddings": 32768,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "rope_theta": 1000000.0,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.0",
  "vision_config": {
    "hidden_size": 1536,
    "intermediate_size": 6144,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "image_size": 420,
    "patch_size": 14,
    "num_channels": 3
  },
  "audio_config": {
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "num_hidden_layers": 12,
    "num_attention_heads": 16,
    "num_mel_bins": 128,
    "max_source_positions": 3000
  }
}