Janus-Pro-7B-bnb-4bit / config.json
cyan2k's picture
Upload MultiModalityCausalLM
f90ae86 verified
{
"_name_or_path": "deepseek-ai/Janus-Pro-7B",
"aligner_config": {
"cls": "MlpProjector",
"model_type": "aligner",
"params": {
"depth": 2,
"input_dim": 1024,
"n_embed": 4096,
"projector_type": "mlp_gelu"
}
},
"architectures": [
"MultiModalityCausalLM"
],
"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": {
"_attn_implementation_autoset": true,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_hidden_layers": 30,
"torch_dtype": "bfloat16",
"vocab_size": 102400
},
"model_type": "multi_modality",
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"torch_dtype": "float16",
"transformers_version": "4.48.1",
"vision_config": {
"cls": "CLIPVisionTower",
"model_type": "vision",
"params": {
"image_size": 384,
"model_name": "siglip_large_patch16_384",
"select_feature": "same",
"select_layer": -1
}
}
}