LLaMA-Factory-Mirror/examples/inference/llava1_5.yaml

model_name_or_path: llava-hf/llava-1.5-7b-hf
template: vicuna
visual_inputs: true
1. fix output_dir in llama3_lora_pretrain.yaml 2. add llava1_5.yaml for inference 2024-07-13 13:16:22 +08:00			`model_name_or_path: llava-hf/llava-1.5-7b-hf`
			`template: vicuna`
Update llava1_5.yaml 2024-07-13 20:30:06 +08:00			`visual_inputs: true`