{ "english": { "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "float32", "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": true, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": [ "VisionEncoderDecoderModel" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "/home/ampixa/ocr/models/trocr-small-handwritten-b4648cfa", "transformers_version": "4.57.6", "decoder": { "vocab_size": 64044, "d_model": 256, "decoder_layers": 6, "decoder_attention_heads": 8, "decoder_ffn_dim": 1024, "activation_function": "relu", "max_position_embeddings": 512, "dropout": 0.1, "attention_dropout": 0.0, "activation_dropout": 0.0, "init_std": 0.02, "decoder_layerdrop": 0.0, "use_cache": false, "scale_embedding": true, "use_learned_position_embeddings": true, "layernorm_embedding": true, "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "float32", "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": true, "cross_attention_hidden_size": 384, "add_cross_attention": true, "tie_encoder_decoder": false, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 0, "pad_token_id": 1, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": 2, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "classifier_dropout": 0.0, "use_bfloat16": false, "tf_legacy_loss": false, "model_type": "trocr", "output_attentions": false }, "encoder": { "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "float32", "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "use_bfloat16": false, "tf_legacy_loss": false, "hidden_size": 384, "num_hidden_layers": 12, "num_attention_heads": 6, "intermediate_size": 1536, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "attention_probs_dropout_prob": 0.0, "initializer_range": 0.02, "layer_norm_eps": 1e-12, "image_size": 384, "patch_size": 16, "num_channels": 3, "qkv_bias": true, "encoder_stride": 16, "pooler_output_size": 384, "pooler_act": "tanh", "model_type": "deit", "output_attentions": false }, "model_type": "vision-encoder-decoder", "tf_legacy_loss": false, "use_bfloat16": false, "output_attentions": false }, "character": { "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "float32", "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": true, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": [ "VisionEncoderDecoderModel" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "/home/ampixa/ocr/ocr-deva-ft/runs/trocr-character-full24000-r1-20261021/milestones/24000", "transformers_version": "4.57.6", "decoder": { "vocab_size": 573, "d_model": 256, "decoder_layers": 6, "decoder_attention_heads": 8, "decoder_ffn_dim": 1024, "activation_function": "relu", "max_position_embeddings": 512, "dropout": 0.1, "attention_dropout": 0.0, "activation_dropout": 0.0, "init_std": 0.02, "decoder_layerdrop": 0.0, "use_cache": false, "scale_embedding": true, "use_learned_position_embeddings": true, "layernorm_embedding": true, "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "float32", "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": true, "cross_attention_hidden_size": 384, "add_cross_attention": true, "tie_encoder_decoder": false, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 0, "pad_token_id": 1, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": 2, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "classifier_dropout": 0.0, "tf_legacy_loss": false, "use_bfloat16": false, "model_type": "trocr", "output_attentions": false }, "encoder": { "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "float32", "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "tf_legacy_loss": false, "use_bfloat16": false, "hidden_size": 384, "num_hidden_layers": 12, "num_attention_heads": 6, "intermediate_size": 1536, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "attention_probs_dropout_prob": 0.0, "initializer_range": 0.02, "layer_norm_eps": 1e-12, "image_size": 384, "patch_size": 16, "num_channels": 3, "qkv_bias": true, "encoder_stride": 16, "pooler_output_size": 384, "pooler_act": "tanh", "model_type": "deit", "output_attentions": false }, "model_type": "vision-encoder-decoder", "tf_legacy_loss": false, "use_bfloat16": false, "output_attentions": false }, "english_generation": { "max_length": 20, "max_new_tokens": null, "min_length": 0, "min_new_tokens": null, "early_stopping": false, "max_time": null, "stop_strings": null, "do_sample": false, "num_beams": 1, "use_cache": false, "cache_implementation": null, "cache_config": null, "return_legacy_cache": null, "prefill_chunk_size": null, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "min_p": null, "typical_p": 1.0, "epsilon_cutoff": 0.0, "eta_cutoff": 0.0, "repetition_penalty": 1.0, "encoder_repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "bad_words_ids": null, "renormalize_logits": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "sequence_bias": null, "token_healing": false, "guidance_scale": null, "watermarking_config": null, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "output_logits": null, "return_dict_in_generate": false, "pad_token_id": 1, "bos_token_id": 0, "eos_token_id": 2, "encoder_no_repeat_ngram_size": 0, "decoder_start_token_id": 2, "is_assistant": false, "num_assistant_tokens": 20, "num_assistant_tokens_schedule": "constant", "assistant_confidence_threshold": 0.4, "prompt_lookup_num_tokens": null, "max_matching_ngram_size": null, "assistant_early_exit": null, "assistant_lookbehind": 10, "target_lookbehind": 10, "disable_compile": false, "low_memory": null, "penalty_alpha": null, "dola_layers": null, "diversity_penalty": 0.0, "num_beam_groups": 1, "constraints": null, "force_words_ids": null, "_from_model_config": true, "transformers_version": "4.57.6" }, "character_generation": { "max_length": 20, "max_new_tokens": 257, "min_length": 0, "min_new_tokens": null, "early_stopping": false, "max_time": null, "stop_strings": null, "do_sample": false, "num_beams": 1, "use_cache": false, "cache_implementation": null, "cache_config": null, "return_legacy_cache": null, "prefill_chunk_size": null, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "min_p": null, "typical_p": 1.0, "epsilon_cutoff": 0.0, "eta_cutoff": 0.0, "repetition_penalty": 1.0, "encoder_repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "bad_words_ids": null, "renormalize_logits": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": [ 0, 1, 3 ], "begin_suppress_tokens": null, "sequence_bias": null, "token_healing": false, "guidance_scale": null, "watermarking_config": null, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "output_logits": null, "return_dict_in_generate": false, "pad_token_id": 1, "bos_token_id": 0, "eos_token_id": 2, "encoder_no_repeat_ngram_size": 0, "decoder_start_token_id": 2, "is_assistant": false, "num_assistant_tokens": 20, "num_assistant_tokens_schedule": "constant", "assistant_confidence_threshold": 0.4, "prompt_lookup_num_tokens": null, "max_matching_ngram_size": null, "assistant_early_exit": null, "assistant_lookbehind": 10, "target_lookbehind": 10, "disable_compile": false, "low_memory": null, "penalty_alpha": null, "dola_layers": null, "diversity_penalty": 0.0, "num_beam_groups": 1, "constraints": null, "force_words_ids": null, "_from_model_config": true, "transformers_version": "4.57.6" } }