|
{ |
|
"_commit_hash": null, |
|
"architectures": [ |
|
"ImageBindModel" |
|
], |
|
"audio_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"add_kv_bias": true, |
|
"architectures": null, |
|
"attention_dropout": 0.0, |
|
"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, |
|
"dropout": 0.0, |
|
"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": "quick_gelu", |
|
"hidden_size": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"image_size": 30, |
|
"initializer_factor": 1.0, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 37, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-06, |
|
"learnable_logit_scale": false, |
|
"length_penalty": 1.0, |
|
"logit_scale_init_value": 20.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 4, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_channels": 1, |
|
"num_hidden_layers": 5, |
|
"num_mel_bins": 128, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"patch_size": 16, |
|
"prefix": null, |
|
"problem_type": null, |
|
"projection_dim": 32, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"stride": 10, |
|
"suppress_tokens": null, |
|
"target_len": 204, |
|
"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, |
|
"transformers_version": "4.35.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"depth_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"add_kv_bias": true, |
|
"architectures": null, |
|
"attention_dropout": 0.0, |
|
"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": 0.0, |
|
"dropout": 0.0, |
|
"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": "quick_gelu", |
|
"hidden_size": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"image_size": 30, |
|
"initializer_factor": 1.0, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 37, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-06, |
|
"learnable_logit_scale": false, |
|
"length_penalty": 1.0, |
|
"logit_scale_init_value": 5.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 4, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_channels": 1, |
|
"num_hidden_layers": 5, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"patch_size": 2, |
|
"prefix": null, |
|
"problem_type": null, |
|
"projection_dim": 32, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"stride": 2, |
|
"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, |
|
"transformers_version": "4.35.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"imu_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"add_kv_bias": true, |
|
"architectures": null, |
|
"attention_dropout": 0.0, |
|
"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": 0.7, |
|
"dropout": 0.0, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"final_dropout": 0.5, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"hidden_act": "quick_gelu", |
|
"hidden_size": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_factor": 1.0, |
|
"initializer_range": 0.02, |
|
"input_shape": [ |
|
6, |
|
30 |
|
], |
|
"intermediate_size": 37, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"kernel_size": 2, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-06, |
|
"learnable_logit_scale": false, |
|
"length_penalty": 1.0, |
|
"logit_scale_init_value": 5.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 4, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 5, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"projection_dim": 32, |
|
"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, |
|
"transformers_version": "4.35.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"initializer_factor": 1.0, |
|
"model_type": "imagebind", |
|
"projection_dim": 32, |
|
"text_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"add_kv_bias": false, |
|
"architectures": null, |
|
"attention_dropout": 0.0, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": 0, |
|
"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": 0.0, |
|
"dropout": 0.0, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": 2, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"hidden_act": "quick_gelu", |
|
"hidden_size": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_factor": 1.0, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 37, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-06, |
|
"learnable_logit_scale": true, |
|
"length_penalty": 1.0, |
|
"logit_scale_init_value": 14.2857, |
|
"max_length": 20, |
|
"max_position_embeddings": 512, |
|
"min_length": 0, |
|
"model_type": "imagebind_text_model", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 4, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 5, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": 1, |
|
"prefix": null, |
|
"problem_type": null, |
|
"projection_dim": 32, |
|
"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, |
|
"transformers_version": "4.35.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"vocab_size": 99 |
|
}, |
|
"thermal_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"add_kv_bias": true, |
|
"architectures": null, |
|
"attention_dropout": 0.0, |
|
"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": 0.0, |
|
"dropout": 0.0, |
|
"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": "quick_gelu", |
|
"hidden_size": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"image_size": 30, |
|
"initializer_factor": 1.0, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 37, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-06, |
|
"learnable_logit_scale": false, |
|
"length_penalty": 1.0, |
|
"logit_scale_init_value": 10.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 4, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_channels": 1, |
|
"num_hidden_layers": 5, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"patch_size": 2, |
|
"prefix": null, |
|
"problem_type": null, |
|
"projection_dim": 32, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"stride": 2, |
|
"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, |
|
"transformers_version": "4.35.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"torch_dtype": "float32", |
|
"transformers_version": null, |
|
"vision_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"add_kv_bias": false, |
|
"architectures": null, |
|
"attention_dropout": 0.0, |
|
"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": 0.0, |
|
"dropout": 0.0, |
|
"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": "quick_gelu", |
|
"hidden_size": 32, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"image_size": 30, |
|
"initializer_factor": 1.0, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 37, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_eps": 1e-06, |
|
"learnable_logit_scale": false, |
|
"length_penalty": 1.0, |
|
"logit_scale_init_value": null, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "imagebind_vision_model", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 4, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_channels": 3, |
|
"num_frames": 2, |
|
"num_hidden_layers": 5, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"patch_size": [ |
|
2, |
|
2, |
|
2 |
|
], |
|
"prefix": null, |
|
"problem_type": null, |
|
"projection_dim": 32, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"stride": [ |
|
2, |
|
2, |
|
2 |
|
], |
|
"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, |
|
"transformers_version": "4.35.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
} |
|
} |
|
|