{ "architectures": [ "GroveForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bbox_token_idx": 32002, "bop_token_idx": 32005, "bos_token_id": 1, "ce_loss_weight": 1.0, "eop_token_idx": 32006, "eos_token_id": 2, "freeze_mlp_adapter": true, "freeze_mm_mlp_adapter": true, "freeze_mm_vision_resampler": false, "giou_loss_weight": 1.0, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "image_aspect": "square", "image_aspect_ratio": "square", "image_grid_pinpoints": null, "image_grid_points": null, "initializer_range": 0.02, "intermediate_size": 11008, "max_length": null, "max_position_embeddings": 4096, "mlp_bias": false, "mm_hidden_size": 1024, "mm_projector_type": "mlp2x_gelu", "mm_resampler_type": null, "mm_use_im_patch_token": false, "mm_use_im_start_end": true, "mm_use_image_start_end": true, "mm_vision_module": "openai/clip-vit-large-patch14-336", "mm_vision_select_feature": "patch", "mm_vision_select_layer": -2, "mm_vision_tower": "openai/clip-vit-large-patch14-336", "model_type": "grove", "num_attention_heads": 32, "num_frames": 8, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_level_reg_features": 4, "num_reg_features": 4, "out_dim": 256, "pad_token_id": 0, "pretrain_mm_mlp_adapter": null, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "select_feature_type": "patch", "special_tokens": {}, "temp_objectness_loss_weight": 1.0, "temp_objectness_threshold": 0.5, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "train_mask_decoder": true, "transformers_version": "4.46.3", "tune_mlp_adapter": false, "tune_mm_mlp_adapter": false, "tune_mm_vision_resampler": false, "unfreeze_mm_vision_tower": false, "use_cache": false, "use_image_patch_token": false, "use_mm_proj": true, "use_temp_objectness": true, "vision_module": "openai/clip-vit-large-patch14-336", "vision_tower": "openai/clip-vit-large-patch14-336", "vocab_size": 32010, "with_region": true }