{ "architectures": [ "MiniCPMOcrForConditionalGeneration" ], "model_type": "minicpm_ocr", "flm_version": "1.0.12", "attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "dtype": "bfloat16", "bos_token_id": 248045, "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention" ], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 16, "linear_value_head_dim": 128, "mamba_ssm_dtype": "float32", "max_position_embeddings": 262144, "mlp_only_layers": [], "mtp_num_hidden_layers": 0, "mtp_use_dedicated_embeddings": false, "num_attention_heads": 8, "num_hidden_layers": 24, "num_key_value_heads": 2, "partial_rotary_factor": 0.25, "rms_norm_eps": 1e-06, "tie_word_embeddings": true, "use_cache": true, "vocab_size": 248100, "rope_parameters": { "rope_type": "default", "rope_theta": 10000000, "partial_rotary_factor": 0.25 }, "addr_qk": 53248, "addr_kv": 53536, "vision_model_weight": "vision_weight.q4nx", "image_token_id": 248056, "video_token_id": 248057, "downsample_mode": "4x", "vision_config": { "MINICPM_OCR_PATCH_SIZE": 14, "MINICPM_OCR_IMAGE_SIZE": 980, "MINICPM_OCR_MAX_SLICE_NUMS": 9, "MINICPM_OCR_SPATIAL_MERGE_SIZE": 2, "MINICPM_OCR_TEMPORAL_PATCH_SIZE": 1, "MINICPM_OCR_DOWNSAMPLE_FACTOR": 4, "MINICPM_OCR_VISION_RESCALE_FACTOR": 0.00392156862745098, "MINICPM_OCR_VISION_RESCALE_IMAGE_MEAN": 0.5, "MINICPM_OCR_VISION_RESCALE_IMAGE_STD": 0.5, "MINICPM_OCR_VISION_EMBED_DIM": 1152, "MINICPM_OCR_VISION_NUM_HEADS": 16, "MINICPM_OCR_VISION_HEAD_DIM": 72, "MINICPM_OCR_VISION_MLP_INTERMEDIATE_SIZE": 4304, "MINICPM_OCR_VISION_NUM_POSITION_EMBEDDINGS": 4900, "MINICPM_OCR_VISION_NUM_LAYERS": 27, "MINICPM_OCR_VISION_LAYER_NORM_EPSILON": 1e-06, "MINICPM_OCR_VISION_OUT_HIDDEN_SIZE": 1024, "MINICPM_OCR_MERGER_HIDDEN_SIZE": 4608 } }