Spaces:

Vision-CAIR
/

MiniGPT-v2

Running on A10G

MiniGPT-v2 / eval_configs /minigpt4_llama2_eval.yaml

Upload 131 files

52ca9c9 8 months ago

No virus

434 Bytes

	model:
	arch: minigpt4
	model_type: pretrain_llama2
	max_txt_len: 160
	end_sym: "</s>"
	low_resource: True
	prompt_template: '[INST] {} [/INST] '
	ckpt: 'please set this value to the path of pretrained checkpoint'


	datasets:
	cc_sbu_align:
	vis_processor:
	train:
	name: "blip2_image_eval"
	image_size: 224
	text_processor:
	train:
	name: "blip_caption"

	run:
	task: image_text_pretrain