{ "model_type": "llava_next_video", "num_labels": 2, "architectures": [ "BertForSequenceClassification" ], "bert_config": { "hidden_size": 768, "num_attention_heads": 12, "num_hidden_layers": 12, "intermediate_size": 3072, "hidden_act": "gelu", "initializer_range": 0.02, "layer_norm_eps": 1e-12 }, "tokenizer_class": "BertTokenizer" }