| { |
| "_vocab_size": 257152, |
| "architectures": [ |
| "DIVEdoc" |
| ], |
| "bos_token_id": 2, |
| "eos_token_id": 1, |
| "hidden_size": 2048, |
| "image_token_index": 257152, |
| "model_type": "DIVEdoc", |
| "pad_token_id": 0, |
| "projection_dim": 2048, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "head_dim": 256, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_activation": null, |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 8192, |
| "model_type": "gemma", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 18, |
| "num_image_tokens": 4096, |
| "num_key_value_heads": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 10000.0, |
| "torch_dtype": "float32", |
| "use_cache": true, |
| "vocab_size": 257216 |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.0", |
| "vision_config": { |
| "_attn_implementation_autoset": true, |
| "encoder_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "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, |
| "depths": [ |
| 2, |
| 2, |
| 14, |
| 2 |
| ], |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "drop_path_rate": 0.1, |
| "early_stopping": false, |
| "embed_dim": 128, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": null, |
| "exponential_decay_length_penalty": null, |
| "ffpos_at_beg": false, |
| "ffpos_at_block": false, |
| "ffpos_at_output": false, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": [ |
| 2048, |
| 2048 |
| ], |
| "initializer_range": 0.02, |
| "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, |
| "mlp_ratio": 4.0, |
| "model_type": "donut-swin", |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_channels": 3, |
| "num_heads": [ |
| 4, |
| 8, |
| 16, |
| 32 |
| ], |
| "num_layers": 4, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "patch_size": 4, |
| "path_norm": true, |
| "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": null, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_absolute_embeddings": false, |
| "use_bfloat16": false, |
| "window_size": 10 |
| }, |
| "ffpos_at_output": true, |
| "model_type": "swinpam", |
| "pam_config": { |
| "_attn_implementation_autoset": false, |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "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, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "pam", |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "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, |
| "sequence_mapping_layer_type": null, |
| "student_embedding_dim": 1024, |
| "student_fmap_dim": [ |
| 64, |
| 64 |
| ], |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "teacher_embedding_dim": 1152, |
| "teacher_fmap_dim": [ |
| 64, |
| 64 |
| ], |
| "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, |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| }, |
| "projection_dim": 2048, |
| "torch_dtype": "float32" |
| } |
| } |
|
|
