diff --git a/1/config.json b/1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/1/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/1/flax_model.msgpack b/1/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..f9df5880a803a61e4c612a5f96c9c446abd7fb1c --- /dev/null +++ b/1/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91cd41430a21f5f850e84ab107ee2281636640f8d2f10d3bbc7875e14fb206d8 +size 851566424 diff --git a/10/config.json b/10/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/10/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/10/flax_model.msgpack b/10/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..4e7d7f7e7e3cc7872344dc301ea938b0965adf5a --- /dev/null +++ b/10/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b688e9d1ef5523d69e490937244975a71454881100aa56fa082748d5b9b62c6 +size 851566424 diff --git a/11/config.json b/11/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/11/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/11/flax_model.msgpack b/11/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..17d9244dea3fb6c9f3ecd4b11a6d12f15bf9b910 --- /dev/null +++ b/11/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60c73ee8849789a0b7ba9a65fcf4cc0d965fe5c6436a1fe230e9d85810e0b58 +size 851566424 diff --git a/12/config.json b/12/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/12/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/12/flax_model.msgpack b/12/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..8a186f6382a7d0baf26c7dc125912a7eb9e952fc --- /dev/null +++ b/12/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8f1cd5748f54256a4744259f8d6e4c3c65aa004f3a6242c6e8acc719aa9111 +size 851566424 diff --git a/13/config.json b/13/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/13/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/13/flax_model.msgpack b/13/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..db94ffc62d86c3830110f6d432bc70deea473c55 --- /dev/null +++ b/13/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af15b2801ee72b348cdb5770dbf25f4e5991e59a5cb029a8c944ca754d631d7 +size 851566424 diff --git a/14/config.json b/14/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/14/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/14/flax_model.msgpack b/14/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..82db79694d0edb2b149e0ff5a6928ae76712940a --- /dev/null +++ b/14/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce27ac2af40bf4b90376d5889677a2570f972c1e0130c981bc560341f1bfd65e +size 851566424 diff --git a/15/config.json b/15/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/15/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/15/flax_model.msgpack b/15/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..b40bc3797583728fdf2a87a659bca48ee9322575 --- /dev/null +++ b/15/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240f4fe5dc0f40f2d8e31525c2ac761931e30c1d066f802b82c3190428b4ccd7 +size 851566424 diff --git a/16/config.json b/16/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/16/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/16/flax_model.msgpack b/16/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..bb998e5ab5703a84b724de7cdbffbcbad09bfaae --- /dev/null +++ b/16/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a518c66ea64d7e493d11860c03663754e075a5876de0eeb1c1c43b0271f2da +size 851566424 diff --git a/17/config.json b/17/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/17/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/17/flax_model.msgpack b/17/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..badac0f3f273659291daf0ab6b9de049091e6371 --- /dev/null +++ b/17/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f36850f2a1194bb5af12e8ded20ba4c8e832c4b1d8df3af94d8a62e4d04053 +size 851566424 diff --git a/18/config.json b/18/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/18/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/18/flax_model.msgpack b/18/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..c3a47c74207280958778ed7234fc14bc7e1d2fc0 --- /dev/null +++ b/18/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8012d67d5a34acb9d5f46667470699b7817022b2fcda1149cd31697a6434ab0e +size 851566424 diff --git a/19/config.json b/19/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/19/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/19/flax_model.msgpack b/19/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..14ff59ea6e809cd4a33c2ce1bd7c44b22f396963 --- /dev/null +++ b/19/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a23bd5420080cff32928c6b9ef894453b874070bbd0af2b9d4c604b2207919 +size 851566424 diff --git a/2/config.json b/2/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/2/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/2/flax_model.msgpack b/2/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..033ca1ead69881cc6fa57a50bcbaca29647e7604 --- /dev/null +++ b/2/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647efee73c66ba3fc8bbba7ef96919da8131a861bb8ab6f8c84b5434db1032ae +size 851566424 diff --git a/20/config.json b/20/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/20/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/20/flax_model.msgpack b/20/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..5124bad82ab5cd8c4bf5857e834c2cb89acc00cd --- /dev/null +++ b/20/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451369296e56171b88aa429326fd651e3096dc3eaac978292efba28e4e819128 +size 851566424 diff --git a/21/config.json b/21/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/21/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/21/flax_model.msgpack b/21/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..98d1c454903a684edb25aa1450e1d37fc3ec84ad --- /dev/null +++ b/21/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf0fdd2cec8ace7a7bb7c7f4d2b293e90408324f04f00fe920198d228e989c1 +size 851566424 diff --git a/22/config.json b/22/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/22/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/22/flax_model.msgpack b/22/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..9023415fd800fdabae88f4f64320d7e647333395 --- /dev/null +++ b/22/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f836c3f07e91793323df1243e7b012fdf45928c60b5218fe408a364430d4e5c +size 851566424 diff --git a/23/config.json b/23/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/23/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/23/flax_model.msgpack b/23/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..3635281b7b43678d20e7200823e7be2f8d910895 --- /dev/null +++ b/23/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf416daa7d9cf87ae89e19b86be8957163f2bd8af81bfe60d96a32ee43e7d22 +size 851566424 diff --git a/24/config.json b/24/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/24/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/24/flax_model.msgpack b/24/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..653150247bccc31a22153cdecaeeadc738d2902d --- /dev/null +++ b/24/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f577daf549fe9fad8ee3ddb3fc4cb780928a900c4b5f9358182c2bc6f89d1c +size 851566424 diff --git a/25/config.json b/25/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/25/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/25/flax_model.msgpack b/25/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..3d81bbcde9d1079cc185a2870e42ee11c2f750ab --- /dev/null +++ b/25/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9453ca5687afdec8f8385a06cebaaf5a1cdbd0b5b1c0bb78c45484f2d9d99e9f +size 851566424 diff --git a/26/config.json b/26/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/26/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/26/flax_model.msgpack b/26/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..da39d148a73f889353b3d7f3a203a0306c1b88bf --- /dev/null +++ b/26/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a84673136aeb0c9cd982bf87a641f91b5ab000ea0494b06bf66467c7904dea5 +size 851566424 diff --git a/27/config.json b/27/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/27/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/27/flax_model.msgpack b/27/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..5f80058b7a4c67ca84f3dc6dcfa119cc271ed739 --- /dev/null +++ b/27/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d450f443e9bac3880d7fb7e9def53ea9beeb4131c7cc9820239324c464e0deb +size 851566424 diff --git a/28/config.json b/28/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/28/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/28/flax_model.msgpack b/28/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..af233469a5aa46e97f7af170b37f91ca3d9fb5a8 --- /dev/null +++ b/28/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9a81871888bd762b062803b48bd29ebe0f1ffb137c6a27dbea3a4ce4051f74 +size 851566424 diff --git a/29/config.json b/29/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/29/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/29/flax_model.msgpack b/29/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..b4527ad870d49c7d519a4342624f8edf776da694 --- /dev/null +++ b/29/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f26c98d8c38248c43ac6c4780e4093d8c2b6600d6c8213db6417143c8944bf7 +size 851566424 diff --git a/3/config.json b/3/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/3/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/3/flax_model.msgpack b/3/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..4be1b909d036adcb79492439bdc96eb2232515c4 --- /dev/null +++ b/3/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee95fec2497d4a6726d7705af060f7be41cb9ce80372161a50367d4a85c09da +size 851566424 diff --git a/30/config.json b/30/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/30/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/30/flax_model.msgpack b/30/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..37b035a0ad3b8b9e15482c2bac41ca704214bcef --- /dev/null +++ b/30/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb23f45c56415e8bc3b1f6389a18ffd2ceaf90da78f6b59db7b2ba84cb6440a +size 851566424 diff --git a/31/config.json b/31/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/31/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/31/flax_model.msgpack b/31/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..0dba04e990db197929649a764704c095a0485e4c --- /dev/null +++ b/31/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b6763a3d623e9ad3ca68964705d1343d47f264bb43fda597ebd8c30efd23e2 +size 851566424 diff --git a/32/config.json b/32/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/32/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/32/flax_model.msgpack b/32/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..c5adf2f1368a81c72338c62d38945ac8d5caaf0b --- /dev/null +++ b/32/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f38474be2e0ceada4d16e66bc1772622051c5db2416189f3168339adbd6837 +size 851566424 diff --git a/33/config.json b/33/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/33/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/33/flax_model.msgpack b/33/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..bd4eab7ca38e1e05705ce5e37b976bb62d345b62 --- /dev/null +++ b/33/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88563d455618d661a99cf9d3f4ea956a55a98dc0eef32d5b407c1c514baf38a +size 851566424 diff --git a/34/config.json b/34/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/34/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/34/flax_model.msgpack b/34/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..4397a153809ce923d09e48ad4e02f507e4c5087d --- /dev/null +++ b/34/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f06d3c5156894a9c005ac47e697abb5e3767d5af3e11363b546d3dd309340d +size 851566424 diff --git a/35/config.json b/35/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/35/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/35/flax_model.msgpack b/35/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..ed27f4b8044b6e69c04f50bbe57161a7e9825725 --- /dev/null +++ b/35/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cda36218773401f2e08de3d427b05f99bc2643b01ff512d0716f1faa5911d52 +size 851566424 diff --git a/36/config.json b/36/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/36/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/36/flax_model.msgpack b/36/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..416550bed252100c8d95c870041b0bd4c8b64cdf --- /dev/null +++ b/36/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8046c9cadf095dc5117d21daa960afbc573a572dd3b61218e9a16ef6e7baa574 +size 851566424 diff --git a/37/config.json b/37/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/37/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/37/flax_model.msgpack b/37/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..49cc0d354cc56b94d0b253ecb3b88d2767bce31e --- /dev/null +++ b/37/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f0a50ff0d3e853227a463ed860f02ad4ce993fb8bb9c677ba5b28312236062 +size 851566424 diff --git a/38/config.json b/38/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/38/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/38/flax_model.msgpack b/38/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..198941f53991eec0e69888f163b23040a995b9e3 --- /dev/null +++ b/38/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58e28357a126948ebbd7755b8306b89e8d659b74cc41513986ab8031eeedef9 +size 851566424 diff --git a/39/config.json b/39/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/39/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/39/flax_model.msgpack b/39/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..918434e8e0bd33eafaba6232329bcc7e7f5fc1b2 --- /dev/null +++ b/39/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9891474d801d3f836332e87a7a6b78a1916d62e22c5fad9e6dc330c994083a +size 851566424 diff --git a/4/config.json b/4/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/4/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/4/flax_model.msgpack b/4/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..380bfd176bc8bf6b99ce37017c0077fe8bc01578 --- /dev/null +++ b/4/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd7b003be02ee9ed0bda0b840e5d902c5b366a6a4e1a38c145f493a0e4feb5a +size 851566424 diff --git a/40/config.json b/40/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/40/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/40/flax_model.msgpack b/40/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..e841256a0d30a286cc0c66593a38289a47809800 --- /dev/null +++ b/40/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5487fc5fc1e2e815f54eab71e97bf9165dba6949cca623952dd2bdea47f4be7e +size 851566424 diff --git a/5/config.json b/5/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/5/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/5/flax_model.msgpack b/5/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..b6002ae43089264f0b6af646a73df08dbb177e7c --- /dev/null +++ b/5/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20948371bb5be12c2eeabed3c46035b98d13f714c7cad32ccebc31b45f43e8a5 +size 851566424 diff --git a/6/config.json b/6/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/6/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/6/flax_model.msgpack b/6/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..b47d2c3428efe991a36dbf43a57b32fb54645521 --- /dev/null +++ b/6/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb5c87ba26e515ae7efa5ed36038ced59babda153ef36db8304d3c4390aee4f +size 851566424 diff --git a/7/config.json b/7/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/7/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/7/flax_model.msgpack b/7/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..61871074f697c621f535207d75567fa73c7823d4 --- /dev/null +++ b/7/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abe068fc162a841d84e653b8301bae4f55579feedff423c96fbf6dab5935efa +size 851566424 diff --git a/8/config.json b/8/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/8/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/8/flax_model.msgpack b/8/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..f32111c00968d92199d8bc857be7fea904c85252 --- /dev/null +++ b/8/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d375635aed374808230a5a020407fcf9533701240def579193ebb6bd21600b +size 851566424 diff --git a/9/config.json b/9/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe3472ebc544363984879cedc42dad55ed8bb15 --- /dev/null +++ b/9/config.json @@ -0,0 +1,165 @@ +{ + "architectures": [ + "HybridCLIP" + ], + "freeze_backbones": false, + "initializer_factor": 1.0, + "model_type": "hybrid-clip", + "projection_dim": 512, + "seed": 42, + "text_config": { + "_name_or_path": "roberta-base", + "add_cross_attention": false, + "architectures": [ + "RobertaForMaskedLM" + ], + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "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": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "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": 514, + "min_length": 0, + "model_type": "roberta", + "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, + "position_embedding_type": "absolute", + "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": "4.21.0", + "type_vocab_size": 1, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 50265 + }, + "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, + "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, + "model_type": "clip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "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": "4.21.0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/9/flax_model.msgpack b/9/flax_model.msgpack new file mode 100644 index 0000000000000000000000000000000000000000..1e8b19535b3e21d0e993f32d0688b4f71319849f --- /dev/null +++ b/9/flax_model.msgpack @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b3c27bc6e41213628740c3d966c3b07e9635bbfecd9b213e264d6474d4591ee +size 851566424 diff --git a/logs/events.out.tfevents.1659504406.27c2761dfe7d.906.0.v2 b/logs/events.out.tfevents.1659504406.27c2761dfe7d.906.0.v2 new file mode 100644 index 0000000000000000000000000000000000000000..e8c9b0dd75c6ae208701632bc8ae36409efa71f1 --- /dev/null +++ b/logs/events.out.tfevents.1659504406.27c2761dfe7d.906.0.v2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10046e4f875404e62bec292d0107cb4580d496d93df6d9bfed9a2bd0da86c306 +size 40 diff --git a/logs/events.out.tfevents.1659507034.27c2761dfe7d.2289.0.v2 b/logs/events.out.tfevents.1659507034.27c2761dfe7d.2289.0.v2 new file mode 100644 index 0000000000000000000000000000000000000000..c7dc2f94cfe1fbc41a2335f740089ff26665e3d9 --- /dev/null +++ b/logs/events.out.tfevents.1659507034.27c2761dfe7d.2289.0.v2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21bd9dc2a17da3aaa82fc8463b3d4a91beaa02ab747e21944da8dbd81040bcbd +size 3514486 diff --git a/logs/events.out.tfevents.1659511663.27c2761dfe7d.6010.0.v2 b/logs/events.out.tfevents.1659511663.27c2761dfe7d.6010.0.v2 new file mode 100644 index 0000000000000000000000000000000000000000..8d54db0fba34d657f396e4f2b628673f34ab9be7 --- /dev/null +++ b/logs/events.out.tfevents.1659511663.27c2761dfe7d.6010.0.v2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399bc794ddbc6db05525208d7a2832ebe29ebb0f7921c4fb0e09de5b798a5ebc +size 380917 diff --git a/logs/events.out.tfevents.1659513593.27c2761dfe7d.8079.0.v2 b/logs/events.out.tfevents.1659513593.27c2761dfe7d.8079.0.v2 new file mode 100644 index 0000000000000000000000000000000000000000..98ee3e702ce9981d82848886ff5ff94a3d21a89f --- /dev/null +++ b/logs/events.out.tfevents.1659513593.27c2761dfe7d.8079.0.v2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3410d2d94c4522c55ef738f2cc63acb5d92bc1437307dbbe49386f7856fb30 +size 380917 diff --git a/logs/events.out.tfevents.1659516319.27c2761dfe7d.10443.0.v2 b/logs/events.out.tfevents.1659516319.27c2761dfe7d.10443.0.v2 new file mode 100644 index 0000000000000000000000000000000000000000..457f4ac4c5f2768be8b6b80e6f93a990b55ea8e1 --- /dev/null +++ b/logs/events.out.tfevents.1659516319.27c2761dfe7d.10443.0.v2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69434e8c9c877c0d0f78fc22908601075b6dfe1e25519bafba133c5d953e9ddb +size 9274048 diff --git a/run_hybrid_clip.py b/run_hybrid_clip.py new file mode 120000 index 0000000000000000000000000000000000000000..7f1cd9dab8aaf6db68ece63e97c1766d5c46b84b --- /dev/null +++ b/run_hybrid_clip.py @@ -0,0 +1 @@ +/root/transformers/examples/flax/summarization/run_hybrid_clip.py \ No newline at end of file