| { | |
| { | |
| "architectures": [ | |
| "MistralForCausalLM", "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50256 | |
| ], | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 24, | |
| "decoder_start_token_id": 50257, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 24, | |
| "eos_token_id": 50256, | |
| "forced_decoder_ids": [ | |
| [ | |
| 1, | |
| 50362 | |
| ] | |
| ], | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_length": 448, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 24, | |
| "num_mel_bins": 80, | |
| "pad_token_id": 50256, | |
| "scale_embedding": false, | |
| "suppress_tokens": [ | |
| 1, | |
| 2, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 14, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31, | |
| 58, | |
| 59, | |
| 60, | |
| 61, | |
| 62, | |
| 63, | |
| 90, | |
| 91, | |
| 92, | |
| 93, | |
| 357, | |
| 366, | |
| 438, | |
| 532, | |
| 685, | |
| 705, | |
| 796, | |
| 930, | |
| 1058, | |
| 1220, | |
| 1267, | |
| 1279, | |
| 1303, | |
| 1343, | |
| 1377, | |
| 1391, | |
| 1635, | |
| 1782, | |
| 1875, | |
| 2162, | |
| 2361, | |
| 2488, | |
| 3467, | |
| 4008, | |
| 4211, | |
| 4600, | |
| 4808, | |
| 5299, | |
| 5855, | |
| 6329, | |
| 7203, | |
| 9609, | |
| 9959, | |
| 10563, | |
| 10786, | |
| 11420, | |
| 11709, | |
| 11907, | |
| 13163, | |
| 13697, | |
| 13700, | |
| 14808, | |
| 15306, | |
| 16410, | |
| 16791, | |
| 17992, | |
| 19203, | |
| 19510, | |
| 20724, | |
| 22305, | |
| 22935, | |
| 27007, | |
| 30109, | |
| 30420, | |
| 33409, | |
| 34949, | |
| 40283, | |
| 40493, | |
| 40549, | |
| 47282, | |
| 49146, | |
| 50257, | |
| 50357, | |
| 50358, | |
| 50359, | |
| 50360, | |
| 50361 | |
| ], | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "xclip", | |
| "projection_dim": 512, | |
| "prompt_alpha": 0.1, | |
| "prompt_attention_dropout": 0.0, | |
| "prompt_hidden_act": "quick_gelu", | |
| "prompt_layers": 2, | |
| "prompt_num_attention_heads": 8, | |
| "prompt_projection_dropout": 0.0, | |
| "text_config": { | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": 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, | |
| "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": 512, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 77, | |
| "min_length": 0, | |
| "model_type": "xclip_text_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 8, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 1, | |
| "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, | |
| "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, | |
| "text_config_dict": null, | |
| "torch_dtype": "float32", | |
| "transformers_version": null, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": 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": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 224, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "mit_hidden_size": 512, | |
| "mit_intermediate_size": 2048, | |
| "mit_num_attention_heads": 8, | |
| "mit_num_hidden_layers": 1, | |
| "model_type": "xclip_vision_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_frames": 8, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 32, | |
| "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, | |
| "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": "4.22.0.dev0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| "vision_config_dict": null | |
| } | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "projection_dim": 768, | |
| "text_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": 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, | |
| "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": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 77, | |
| "min_length": 0, | |
| "model_type": "clip_text_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 12, | |
| "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": 768, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": 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": "4.21.3", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vocab_size": 49408 | |
| }, | |
| "text_config_dict": { | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "projection_dim": 768 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": null, | |
| } | |
| } |