config.json

{
  "_name_or_path": "ICTNLP/stream-omni-8b",
  "add_faster_video": false,
  "add_time_instruction": false,
  "architectures": [
    "StreamOmniLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_vocab_size": 0,
  "bos_token_id": 128000,
  "bottom_audio_layers_lr": 1e-06,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "faster_token_stride": 10,
  "force_sample": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "square",
  "image_crop_resolution": null,
  "image_grid_pinpoints": [
    [
      384,
      768
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      1152,
      384
    ],
    [
      384,
      1152
    ]
  ],
  "image_split_resolution": null,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "mm_hidden_size": 1152,
  "mm_newline_position": "grid",
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_spatial_pool_mode": "bilinear",
  "mm_spatial_pool_stride": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "google/siglip-so400m-patch14-384",
  "mm_vision_tower_lr": 2e-06,
  "model_type": "stream_omni_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_top_audio_layers": 5,
  "pos_skipping_range": 4096,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.43.1",
  "use_cache": false,
  "use_mm_proj": true,
  "use_pos_skipping": false,
  "vision_tower_pretrained": null,
  "vocab_size": 132352
}