From 7acb1241c6f9ea1de1b9fe53555dfb60ff1ae6af Mon Sep 17 00:00:00 2001 From: xaedes Date: Fri, 1 Sep 2023 16:04:08 +0200 Subject: [PATCH] update README.md --- examples/finetune/README.md | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/examples/finetune/README.md b/examples/finetune/README.md index 11fe992d0..e034bb2f0 100644 --- a/examples/finetune/README.md +++ b/examples/finetune/README.md @@ -15,8 +15,7 @@ wget https://raw.githubusercontent.com/brunoklein99/deep-learning-notes/master/s --train-data "shakespeare.txt" \ --save-every 10 \ --threads 6 --adam-iter 30 --batch 4 --ctx 64 \ - --use-checkpointing --use-alloc \ - --mem-lora 2 --mem-compute 1 --mem-compute0 20 + --use-checkpointing # predict ./bin/main -m open-llama-3b-v2-q8_0.gguf --lora lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin @@ -28,8 +27,6 @@ The pattern "ITERATION" in the output filenames will be replaced with the iterat Gradient checkpointing reduces the memory requirements by ~50% but increases the runtime. If you have enough RAM, you can make finetuning a bit faster by disabling checkpointing with `--no-checkpointing`. -To change the amount of memory for finetuning with memory allocator (`--use-alloc`, used by default), you can use `--mem-compute0 N` to specify the number of gigabytes. - The LORA rank is configured for each model tensor type separately with these command line options: ```bash