|
{
|
|
"aligner_config": {
|
|
"cls": "MlpProjector",
|
|
"model_type": "aligner",
|
|
"params": {
|
|
"depth": 2,
|
|
"input_dim": 1024,
|
|
"n_embed": 4096,
|
|
"projector_type": "mlp_gelu"
|
|
}
|
|
},
|
|
"gen_aligner_config": {
|
|
"cls": "MlpProjector",
|
|
"model_type": "gen_aligner",
|
|
"params": {
|
|
"depth": 2,
|
|
"input_dim": 8,
|
|
"n_embed": 4096,
|
|
"projector_type": "mlp_gelu"
|
|
}
|
|
},
|
|
"gen_head_config": {
|
|
"cls": "vision_head",
|
|
"model_type": "gen_head",
|
|
"params": {
|
|
"image_token_embed": 4096,
|
|
"image_token_size": 16384,
|
|
"n_embed": 4096
|
|
}
|
|
},
|
|
"gen_vision_config": {
|
|
"cls": "VQ-16",
|
|
"model_type": "gen_vision",
|
|
"params": {
|
|
"image_token_size": 16384,
|
|
"n_embed": 8
|
|
}
|
|
},
|
|
"language_config": {
|
|
"max_position_embeddings": 16384,
|
|
"model_type": "llama",
|
|
"num_hidden_layers": 30,
|
|
"torch_dtype": "bfloat16",
|
|
"vocab_size": 102400
|
|
},
|
|
"model_type": "multi_modality",
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.33.1",
|
|
"vision_config": {
|
|
"cls": "CLIPVisionTower",
|
|
"model_type": "vision",
|
|
"params": {
|
|
"image_size": 384,
|
|
"model_name": "siglip_large_patch16_384",
|
|
"select_feature": "same",
|
|
"select_layer": -1
|
|
}
|
|
}
|
|
}
|
|
|