{ "architectures": [ "GARModel" ], "auto_map": { "AutoConfig": "configuration_gar.GARConfig", "AutoModel": "modeling_gar.GARModel", "AutoModelForCausalLM": "modeling_gar.GARModel" }, "crop_tokens_ids": [ 128004, 128005, 128008, 128010, 128011 ], "kernel_size": [ 14, 14 ], "mask_path_embedding_out_channels": 1024, "mllm_config": { "_name_or_path": "/mnt/bn/zilongdata-us/wangyuhao/model/Perception-LM-1B", "architectures": [ "PerceptionLMForConditionalGeneration" ], "image_token_id": 128002, "model_type": "perception_lm", "projector_pooling_ratio": 2, "text_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 128000, "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": [ 128001, 128009 ], "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 8192, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 11520, "min_length": 0, "mlp_bias": false, "model_type": "llama", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 16, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "pretraining_tp": 1, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "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_bfloat16": false, "use_cache": true, "use_flash_attn": true, "vocab_size": 128262 }, "torch_dtype": "bfloat16", "use_flash_attn": true, "video_token_id": 128003, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architecture": "vit_pe_core_large_patch14_336", "architectures": null, "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_pooling": true, "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, "global_pool": "map", "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label_names": [ "LABEL_0", "LABEL_1" ], "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_args": { "depth": 23, "embed_dim": 1024, "global_pool": "", "img_size": [ 448, 448 ], "init_values": 0.1, "ref_feat_shape": [ 32, 32 ], "use_post_transformer_norm": false }, "model_type": "timm_wrapper", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_classes": 2, "num_features": 1024, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "pretrained_cfg": { "classifier": "head", "crop_mode": "center", "crop_pct": 1.0, "custom_load": false, "first_conv": "patch_embed.proj", "fixed_input_size": true, "input_size": [ 3, 336, 336 ], "interpolation": "bicubic", "license": "custom", "mean": [ 0.5, 0.5, 0.5 ], "pool_size": null, "std": [ 0.5, 0.5, 0.5 ], "tag": "fb" }, "problem_type": null, "pruned_heads": {}, "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_bfloat16": false, "use_flash_attn": false }, "vision_use_cls_token": true }, "model_type": "GAR", "output_attentions": false, "patch_size_h": 14, "patch_size_w": 14, "prompt_numbers": 5, "max_num_tiles": 16, "torch_dtype": "bfloat16", "transformers_version": null }