PaddleOCR-VL-hf / config.json
merve's picture
merve HF Staff
Upload PaddleOCRVLForConditionalGeneration
3ec0cc5 verified
{
"architectures": [
"PaddleOCRVLForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 100295,
"model_type": "paddleocr_vl",
"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": 500000.0,
"rope_type": "default",
"type": "default"
},
"tie_word_embeddings": true,
"use_bias": false,
"use_cache": true,
"vocab_size": 103424
},
"tie_word_embeddings": true,
"transformers_version": "5.2.0.dev0",
"video_token_id": 101307,
"vision_config": {
"attention_dropout": 0.0,
"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,
"patch_size": 14,
"spatial_merge_size": 2
},
"vision_end_token_id": 101306,
"vision_start_token_id": 101305
}