{ "architectures": [ "LlavaForConditionalGeneration" ], "dtype": "float32", "ignore_index": -100, "image_seq_length": 576, "image_token_index": 32000, "model_type": "llava", "multimodal_projector_bias": true, "projector_hidden_act": "gelu", "text_config": { "_name_or_path": "lmsys/vicuna-7b-v1.5", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float16", "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 32000 }, "tie_word_embeddings": false, "transformers_version": "5.3.0", "vision_config": { "add_cross_attention": false, "attention_dropout": 0.0, "bos_token_id": null, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "dropout": 0.0, "eos_token_id": null, "finetuning_task": null, "hidden_act": "quick_gelu", "hidden_size": 1024, "image_size": 336, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "layer_norm_eps": 1e-05, "model_type": "clip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "pad_token_id": null, "patch_size": 14, "prefix": null, "projection_dim": 768, "pruned_heads": {}, "sep_token_id": null, "task_specific_params": null, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "torchscript": false, "use_bfloat16": false }, "vision_feature_layer": -2, "vision_feature_select_strategy": "default" }