| { | |
| "architectures": [ | |
| "PaddleOCRVLForConditionalGeneration" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "compression_ratio": 1.0, | |
| "dtype": "bfloat16", | |
| "hidden_dropout_prob": 0.0, | |
| "ignored_index": -100, | |
| "image_token_id": 100295, | |
| "max_sequence_length": null, | |
| "model_type": "paddleocr_vl", | |
| "quantization_config": { | |
| "include_input_output_embeddings": false, | |
| "modules_to_not_convert": [ | |
| "model.visual", | |
| "model.projector", | |
| "lm_head" | |
| ], | |
| "quant_method": "torchao", | |
| "quant_type": { | |
| "default": { | |
| "_data": { | |
| "granularity": { | |
| "_data": { | |
| "dim": -1 | |
| }, | |
| "_type": "PerRow", | |
| "_version": 1 | |
| }, | |
| "group_size": null, | |
| "set_inductor_config": true | |
| }, | |
| "_type": "Int8WeightOnlyConfig", | |
| "_version": 2 | |
| } | |
| }, | |
| "untie_embedding_weights": false | |
| }, | |
| "rope_is_neox_style": true, | |
| "sliding_window": null, | |
| "text_config": { | |
| "bos_token_id": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 131072, | |
| "model_type": "paddleocr_vl_text", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_theta": 500000, | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "use_bias": false, | |
| "use_cache": false, | |
| "vocab_size": 103424 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.18.0", | |
| "use_3d_rope": true, | |
| "use_flash_attention": false, | |
| "video_token_id": 101307, | |
| "vision_config": { | |
| "architectures": [ | |
| "PaddleOCRVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig", | |
| "AutoModel": "modeling_paddleocr_vl.PaddleOCRVisionModel" | |
| }, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 384, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "paddleocr_vl_vision", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "pad_token_id": 0, | |
| "patch_size": 14, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "axial" | |
| }, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2 | |
| }, | |
| "vision_end_token_id": 101306, | |
| "vision_start_token_id": 101305, | |
| "weight_share_add_bias": true | |
| } | |