{ "architectures": [ "VideoLlama3ForConditionalGeneration" ], "dtype": "bfloat16", "image_token_id": 151655, "model_type": "video_llama_3", "text_config": { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936 }, "transformers_version": "4.57.0.dev0", "video_token_id": 151656, "vision_config": { "attention_dropout": 0.0, "dtype": "bfloat16", "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "initializer_range": 0.02, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "video_llama_3_vision", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14 } }