PaddlePaddle/PaddleOCR-VL
1.7k8.2k
1{2 "architectures": [3 "PaddleOCRVLForConditionalGeneration"4 ],5 "attention_probs_dropout_prob": 0.0,6 "auto_map": {7 "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",8 "AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",9 "AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"10 },11 "compression_ratio": 1.0,12 "head_dim": 128,13 "hidden_act": "silu",14 "hidden_dropout_prob": 0.0,15 "hidden_size": 1024,16 "ignored_index": -100,17 "image_token_id": 100295,18 "intermediate_size": 3072,19 "max_position_embeddings": 131072,20 "max_sequence_length": null,21 "model_type": "paddleocr_vl",22 "num_attention_heads": 16,23 "num_hidden_layers": 18,24 "num_key_value_heads": 2,25 "pad_token_id": 0,26 "rms_norm_eps": 1e-05,27 "rope_scaling": {28 "mrope_section": [29 16,30 24,31 2432 ],33 "rope_type": "default",34 "type": "default"35 },36 "rope_theta": 500000,37 "sliding_window": null,38 "tie_word_embeddings": false,39 "torch_dtype": "bfloat16",40 "transformers_version": "4.55.0",41 "use_bias": false,42 "use_cache": false,43 "use_flash_attention": false,44 "video_token_id": 101307,45 "vision_config": {46 "architectures": [47 "PaddleOCRVisionModel"48 ],49 "attention_dropout": 0.0,50 "auto_map": {51 "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",52 "AutoModel": "modeling_paddleocr_vl.PaddleOCRVisionModel"53 },54 "hidden_act": "gelu_pytorch_tanh",55 "hidden_size": 1152,56 "image_size": 384,57 "intermediate_size": 4304,58 "layer_norm_eps": 1e-06,59 "model_type": "paddleocr_vl",60 "num_attention_heads": 16,61 "num_channels": 3,62 "num_hidden_layers": 27,63 "pad_token_id": 0,64 "patch_size": 14,65 "spatial_merge_size": 2,66 "temporal_patch_size": 2,67 "tokens_per_second": 2,68 "torch_dtype": "bfloat16"69 },70 "vision_start_token_id": 101305,71 "vision_end_token_id": 101306,72 "vocab_size": 103424,73 "weight_share_add_bias": true,74 "use_3d_rope": true,75 "rope_is_neox_style": true76}77 