Dear author, NExT-Chat's capability of fine-grained image comprehension is really fascinating. But when I run bash eval_res.sh with param --per_device_eval_batch_size ...
"/mllm/models/sam/modeling_sam.py:588-615": "Decomposed Relative Positional Embeddings Calculator", "/mllm/models/sam/modeling_sam.py:616-647": "SAM Patch Embedding ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results