|
{ |
|
"_name_or_path": "google/owlvit-base-patch32", |
|
"architectures": [ |
|
"OwlViTForObjectDetection" |
|
], |
|
"initializer_factor": 1.0, |
|
"logit_scale_init_value": 2.6592, |
|
"model_type": "owlvit", |
|
"projection_dim": 512, |
|
"quantization_config": { |
|
"_load_in_4bit": false, |
|
"_load_in_8bit": true, |
|
"bnb_4bit_compute_dtype": "float32", |
|
"bnb_4bit_quant_type": "fp4", |
|
"bnb_4bit_use_double_quant": false, |
|
"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": false, |
|
"load_in_8bit": true, |
|
"quant_method": "bitsandbytes" |
|
}, |
|
"text_config": { |
|
"bos_token_id": 0, |
|
"dropout": 0.0, |
|
"eos_token_id": 2, |
|
"max_length": 16, |
|
"model_type": "owlvit_text_model", |
|
"pad_token_id": 1 |
|
}, |
|
"text_config_dict": null, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.39.0.dev0", |
|
"vision_config": { |
|
"dropout": 0.0, |
|
"model_type": "owlvit_vision_model" |
|
}, |
|
"vision_config_dict": null |
|
} |
|
|