Merge pull request #12 from GreenBitAI/feature/gptq_model

update AutoGPTQ Q-SFT command

Author: yanghaojin

README.md

@@ -131,12 +131,18 @@ The '--tune-qweight-only' parameter determines whether to fine-tune only the qua
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python -m green_bit_llm.sft.finetune --model GreenBitAI/Qwen-1.5-1.8B-layer-mix-bpw-3.0 --dataset tatsu-lab/alpaca --optimizer DiodeMix --tune-qweight-only
+
+# AutoGPTQ model Q-SFT
+CUDA_VISIBLE_DEVICES=0 python -m green_bit_llm.sft.finetune --model astronomer/Llama-3-8B-Instruct-GPTQ-4-Bit --dataset tatsu-lab/alpaca --tune-qweight-only --batch-size 1
 ```
 
 ### Parameter efficient fine-tuning
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 python -m green_bit_llm.sft.peft_lora --model GreenBitAI/Qwen-1.5-1.8B-layer-mix-bpw-3.0 --dataset tatsu-lab/alpaca --lr-fp 1e-6
+
+# AutoGPTQ model with Lora
+CUDA_VISIBLE_DEVICES=0 python -m green_bit_llm.sft.peft_lora --model astronomer/Llama-3-8B-Instruct-GPTQ-4-Bit --dataset tatsu-lab/alpaca --lr-fp 1e-6
 ```
 
 ## License