From 9e0144e2fafe467f9bb721c899172286db55deac Mon Sep 17 00:00:00 2001 From: Niels Rogge Date: Wed, 7 Sep 2022 17:54:02 +0000 Subject: [PATCH] Upload model --- config.json | 328 ++++++++++++++++++++++++++++++++++++++++++++++ pytorch_model.bin | 3 + 2 files changed, 331 insertions(+) create mode 100644 config.json create mode 100644 pytorch_model.bin diff --git a/config.json b/config.json new file mode 100644 index 0000000..ddd077d --- /dev/null +++ b/config.json @@ -0,0 +1,328 @@ +{ + "_commit_hash": null, + "architectures": [ + "XCLIPModel" + ], + "initializer_factor": 1.0, + "logit_scale_init_value": 2.6592, + "model_type": "xclip", + "projection_dim": 512, + "prompt_alpha": 0.1, + "prompt_attention_dropout": 0.0, + "prompt_hidden_act": "quick_gelu", + "prompt_layers": 2, + "prompt_num_attention_heads": 8, + "prompt_projection_dropout": 0.0, + "text_config": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "dropout": 0.0, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "quick_gelu", + "hidden_size": 512, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 2048, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-05, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 77, + "min_length": 0, + "model_type": "xclip_text_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 8, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 1, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.22.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false, + "vocab_size": 49408 + }, + "text_config_dict": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "bos_token_id": 0, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "dropout": 0.0, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "quick_gelu", + "hidden_size": 512, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 2048, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-05, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 77, + "min_length": 0, + "model_type": "xclip_text_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 8, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 1, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.22.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false, + "vocab_size": 49408 + }, + "torch_dtype": "float32", + "transformers_version": null, + "vision_config": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "drop_path_rate": 0.0, + "dropout": 0.0, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "image_size": 224, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-05, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "mit_hidden_size": 512, + "mit_intermediate_size": 2048, + "mit_num_attention_heads": 8, + "mit_num_hidden_layers": 1, + "model_type": "xclip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "num_frames": 32, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "patch_size": 16, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.22.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false + }, + "vision_config_dict": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "drop_path_rate": 0.0, + "dropout": 0.0, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "image_size": 224, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-05, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "mit_hidden_size": 512, + "mit_intermediate_size": 2048, + "mit_num_attention_heads": 8, + "mit_num_hidden_layers": 1, + "model_type": "xclip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "num_frames": 32, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "patch_size": 16, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.22.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..18a6f75 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f57805daf0db792cc4a09e99b72c97feb2b7e7a0a99c219718d28186d852fe4 +size 779959711