| { | |
| "architectures": [ | |
| "NVOmniEmbedModel" | |
| ], | |
| "audio_config": { | |
| "_attn_implementation_autoset": true, | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "attention_dropout": 0.0, | |
| "d_model": 1280, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 32, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "max_source_positions": 1500, | |
| "model_type": "qwen2_5_omni_audio_encoder", | |
| "n_window": 100, | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "output_dim": 2048, | |
| "scale_embedding": false, | |
| "torch_dtype": "bfloat16" | |
| }, | |
| "audio_end_token_id": 151648, | |
| "audio_max_length": 2048000, | |
| "audio_start_token_id": 151647, | |
| "audio_token_index": 151646, | |
| "auto_map": { | |
| "AutoModel": "modeling_nv_omni_embed.NVOmniEmbedModel", | |
| "AutoConfig": "modeling_nv_omni_embed.NVOmniEmbedConfig" | |
| }, | |
| "bos_token_id": 151644, | |
| "eos_token_id": 151645, | |
| "ignore_index": -100, | |
| "image_token_index": 151655, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "model_type": "nvomniembed", | |
| "pad_token_id": 151643, | |
| "position_id_per_seconds": 25, | |
| "resized_height": 680, | |
| "resized_width": 680, | |
| "seconds_per_chunk": 2, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "model_type": "qwen2_5_omni_text", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.0.dev0", | |
| "user_token_id": 872, | |
| "video_token_index": 151656, | |
| "vision_config": { | |
| "_attn_implementation_autoset": true, | |
| "depth": 32, | |
| "embed_dim": 1280, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_omni_vision_encoder", | |
| "num_heads": 16, | |
| "out_hidden_size": 2048, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 25, | |
| "torch_dtype": "bfloat16", | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654 | |
| } | |