{ "_name_or_path": "ZachSun/stllava-med-7b", "architectures": [ "LlavaLlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "freeze_mm_mlp_adapter": false, "hidden_act": "silu", "hidden_size": 4096, "image_aspect_ratio": "pad", "image_grid_pinpoints": null, "initializer_range": 0.02, "intermediate_size": 11008, "loss_alpha": 0.5, "max_position_embeddings": 4096, "mm_hidden_size": 1024, "mm_projector_lr": 2e-05, "mm_projector_type": "cluster", "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": "ZachSun/stllava-med-7b-vit", "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_latents": 256, "pad_token_id": 0, "pretraining_tp": 1, "qav_loss": false, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.40.0.dev0", "tune_mm_mlp_adapter": false, "use_cache": true, "use_mm_proj": true, "vision_tower_lr": 2e-05, "vocab_size": 32000 }