News
torchrun --nproc_per_node 1 example_text_completion.py --ckpt_dir llama-2-7b/ --tokenizer_path tokenizer.model --max_seq_len 128 --max_batch_size 4 I get memory error: RuntimeError: CUDA error: out of ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback