{ "_commit_hash": null, "_name_or_path": "HF_Kosmos2", "architectures": [ "Kosmos2ForConditionalGeneration" ], "latent_query_num": 64, "model_type": "kosmos-2", "auto_map": { "AutoConfig": "configuration_kosmos2.Kosmos2Config", "AutoModel": "modeling_kosmos2.Kosmos2Model", "AutoModelForVision2Seq": "modeling_kosmos2.Kosmos2ForConditionalGeneration", "AutoProcessor": "processing_kosmos2.Kosmos2Processor" }, "text_config": { "_name_or_path": "", "activation_dropout": 0.0, "activation_function": "gelu", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.1, "attention_heads": 32, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "embed_dim": 2048, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "ffn_dim": 8192, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "layers": 24, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 2048, "min_length": 0, "model_type": "kosmos_2_text_model", "no_repeat_ngram_size": 3, "num_beam_groups": 1, "num_beams": 1, "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, "scale_embedding": true, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.31.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 65037 }, "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, "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, "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": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 224, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "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": "kosmos_2_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "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, "projection_dim": 512, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.31.0.dev0", "typical_p": 1.0, "use_bfloat16": false } }