| { | |
| "_name_or_path": "/gpfs/data/fs72723/vtuan/fine-tuning-vla/SpatialVLA/pretrained/spatialvla-4b-224-pt", | |
| "_vocab_size": 265347, | |
| "action_token_begin_idx": 257153, | |
| "architectures": [ | |
| "SpatialVLAForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_spatialvla.SpatialVLAConfig", | |
| "AutoModel": "modeling_spatialvla.SpatialVLAForConditionalGeneration" | |
| }, | |
| "bos_token_id": 2, | |
| "ego3d_patch_reso": 2, | |
| "eos_token_id": 1, | |
| "hidden_size": 2048, | |
| "image_token_index": 257152, | |
| "model_type": "spatialvla", | |
| "n_freqs": 8, | |
| "num_hidden_layers": 26, | |
| "pad_token_id": 0, | |
| "projection_dim": 2304, | |
| "spatial_token_num": 8194, | |
| "text_config": { | |
| "_attn_implementation_autoset": true, | |
| "architectures": [ | |
| "Gemma2ForCausalLM" | |
| ], | |
| "eos_token_id": [ | |
| 1, | |
| 107 | |
| ], | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 2304, | |
| "intermediate_size": 9216, | |
| "model_type": "gemma2", | |
| "num_hidden_layers": 26, | |
| "num_image_tokens": 256, | |
| "num_key_value_heads": 4, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "vocab_size": 265347 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.0", | |
| "use_spatial_token": true, | |
| "use_vision_zoe": true, | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "num_positions": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2304, | |
| "torch_dtype": "bfloat16", | |
| "vision_use_head": false | |
| }, | |
| "vision_zoe_config": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "Intel/zoedepth-nyu-kitti", | |
| "add_cross_attention": false, | |
| "add_projection": false, | |
| "architectures": [ | |
| "ZoeDepthForDepthEstimation" | |
| ], | |
| "attractor_alpha": 1000, | |
| "attractor_gamma": 2, | |
| "attractor_kind": "mean", | |
| "backbone": null, | |
| "backbone_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "add_fpn": false, | |
| "architectures": null, | |
| "attention_probs_dropout_prob": 0.0, | |
| "auxiliary_channels": 256, | |
| "auxiliary_concat_input": false, | |
| "auxiliary_loss_weight": 0.4, | |
| "auxiliary_num_convs": 1, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "drop_path_rate": 0.1, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "layer_scale_init_value": 0.1, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "beit", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "num_return_sequences": 1, | |
| "out_features": [ | |
| "stage6", | |
| "stage12", | |
| "stage18", | |
| "stage24" | |
| ], | |
| "out_indices": [ | |
| 6, | |
| 12, | |
| 18, | |
| 24 | |
| ], | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "pool_scales": [ | |
| 1, | |
| 2, | |
| 3, | |
| 6 | |
| ], | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "reshape_hidden_states": false, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "semantic_loss_ignore_index": 255, | |
| "sep_token_id": null, | |
| "stage_names": [ | |
| "stem", | |
| "stage1", | |
| "stage2", | |
| "stage3", | |
| "stage4", | |
| "stage5", | |
| "stage6", | |
| "stage7", | |
| "stage8", | |
| "stage9", | |
| "stage10", | |
| "stage11", | |
| "stage12", | |
| "stage13", | |
| "stage14", | |
| "stage15", | |
| "stage16", | |
| "stage17", | |
| "stage18", | |
| "stage19", | |
| "stage20", | |
| "stage21", | |
| "stage22", | |
| "stage23", | |
| "stage24" | |
| ], | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_absolute_position_embeddings": false, | |
| "use_auxiliary_head": true, | |
| "use_bfloat16": false, | |
| "use_mask_token": false, | |
| "use_mean_pooling": true, | |
| "use_relative_position_bias": true, | |
| "use_shared_relative_position_bias": false, | |
| "vocab_size": 8192 | |
| }, | |
| "backbone_hidden_size": 1024, | |
| "bad_words_ids": null, | |
| "batch_norm_eps": 1e-05, | |
| "begin_suppress_tokens": null, | |
| "bin_centers_type": "softplus", | |
| "bin_configurations": [ | |
| { | |
| "max_depth": 10.0, | |
| "min_depth": 0.001, | |
| "n_bins": 64, | |
| "name": "nyu" | |
| }, | |
| { | |
| "max_depth": 80.0, | |
| "min_depth": 0.001, | |
| "n_bins": 64, | |
| "name": "kitti" | |
| } | |
| ], | |
| "bin_embedding_dim": 128, | |
| "bos_token_id": null, | |
| "bottleneck_features": 256, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "fusion_hidden_size": 256, | |
| "head_in_index": -1, | |
| "hidden_act": "gelu", | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_temp": 50.0, | |
| "min_length": 0, | |
| "min_temp": 0.0212, | |
| "model_type": "zoedepth", | |
| "neck_hidden_sizes": [ | |
| 256, | |
| 512, | |
| 1024, | |
| 1024 | |
| ], | |
| "no_repeat_ngram_size": 0, | |
| "num_attractors": [ | |
| 16, | |
| 8, | |
| 4, | |
| 1 | |
| ], | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_patch_transformer_layers": 4, | |
| "num_relative_features": 32, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_transformer_hidden_size": 128, | |
| "patch_transformer_intermediate_size": 1024, | |
| "patch_transformer_num_attention_heads": 4, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "readout_type": "project", | |
| "reassemble_factors": [ | |
| 4, | |
| 2, | |
| 1, | |
| 0.5 | |
| ], | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_batch_norm_in_fusion_residual": false, | |
| "use_bfloat16": false, | |
| "use_bias_in_fusion_residual": null, | |
| "use_pretrained_backbone": false | |
| } | |
| } | |