| { | |
| "attn_mode": "sdpa", | |
| "gaze_model_config": { | |
| "connector_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "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_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, | |
| "hidden_dim": 192, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "num_tokens": 196, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "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": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "gaze_decoder_config": { | |
| "_attn_implementation_autoset": false, | |
| "_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": 12800000, | |
| "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": 265, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 32, | |
| "hidden_act": "silu", | |
| "hidden_size": 192, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 384, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 131072, | |
| "min_length": 0, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 6, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 6, | |
| "num_multi_token_pred": 10, | |
| "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": 8.0, | |
| "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": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 266 | |
| }, | |
| "input_img_size": 224, | |
| "model_type": "", | |
| "num_vision_tokens_each_frame": 265, | |
| "vision_model_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "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, | |
| "depth": 1, | |
| "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, | |
| "hidden_dim": 192, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "kernel_size": 16, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "out_dim": 192, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "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, | |
| "temporal_patch_size": 1, | |
| "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, | |
| "trunk_spatial_kernel_size": 3, | |
| "trunk_temporal_kernel_size": 3, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| } | |
| }, | |
| "gazing_ratio_config": { | |
| "exponential": { | |
| "gazing_ratio_max": 1, | |
| "gazing_ratio_min": 0, | |
| "lambda": 10 | |
| }, | |
| "fixed": { | |
| "gazing_ratio": 0.75 | |
| }, | |
| "sample_strategy_during_inference": "fixed", | |
| "sample_strategy_during_training": "fixed", | |
| "uniform": { | |
| "gazing_ratio_max": 1, | |
| "gazing_ratio_min": 0 | |
| } | |
| }, | |
| "gazing_ratio_each_frame_config": { | |
| "dirichlet": { | |
| "alpha": 0.5 | |
| }, | |
| "sample_strategy_during_inference": "uniform", | |
| "sample_strategy_during_training": "self", | |
| "self": null, | |
| "uniform": null | |
| }, | |
| "has_task_loss_requirement_during_inference": true, | |
| "has_task_loss_requirement_during_training": false, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "max_batch_size": null, | |
| "max_num_frames": 16, | |
| "model_type": "autogaze", | |
| "num_vision_tokens_each_frame": 265, | |
| "scales": "32+64+112+224", | |
| "task_loss_requirement_config": { | |
| "fixed": { | |
| "task_loss_requirement": 0.7 | |
| }, | |
| "sample_strategy_during_inference": "fixed", | |
| "sample_strategy_during_training": "uniform", | |
| "uniform": { | |
| "task_loss_requirement_max": 1.0, | |
| "task_loss_requirement_min": 0.5 | |
| } | |
| }, | |
| "transformers_version": "4.51.3", | |
| "use_flash_attn": false | |
| } | |