{ "_commit_hash": "e9754cb57664705bacb62145ea8a977f269a456b", "_name_or_path": "flavour/vtde-dinov2-small-bge-small-en", "architectures": [ "VTDEModel" ], "auto_map": { "AutoConfig": "modelling.VTDEConfig", "AutoModel": "modelling.VTDEModel" }, "logit_scale_init_value": 2.6592, "model_type": "vtde", "projection_dim": 384, "text_config": { "_name_or_path": "BAAI/bge-small-en", "add_cross_attention": false, "architectures": [ "BertModel" ], "attention_probs_dropout_prob": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "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": null, "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": 384, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 1536, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-12, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "min_length": 0, "model_type": "bert", "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": 0, "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, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.32.0.dev0", "type_vocab_size": 2, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 30522 }, "text_pooling_mode": "mean", "torch_dtype": "float32", "transformers_version": null, "vision_config": { "_name_or_path": "facebook/dinov2-small", "add_cross_attention": false, "architectures": [ "Dinov2Model" ], "attention_probs_dropout_prob": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "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": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 384, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 518, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "layerscale_value": 1.0, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "mlp_ratio": 4, "model_type": "dinov2", "no_repeat_ngram_size": 0, "num_attention_heads": 6, "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": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.32.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_swiglu_ffn": false }, "vision_pooling_mode": "max" }