From 8db4633d842f5332407adc547a3a869ac16a0b3e Mon Sep 17 00:00:00 2001 From: John Smith Date: Thu, 30 Mar 2023 11:24:25 +0800 Subject: [PATCH] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 659acca..21bfc9b 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,7 @@ Made some adjust for the code in peft and gptq for llama, and make it possible f * Added pip install support by sterlind, preparing to merge changes upstream * Added V2 model support (with groupsize, both inference + finetune) * Added some options on finetune: set default to use eos_token instead of padding, add resume_checkpoint to continue training +* Added offload support. load_llama_model_4bit_low_ram_and_offload_to_cpu function can be used. # Requirements gptq-for-llama: https://github.com/qwopqwop200/GPTQ-for-LLaMa