Open whk6688 opened 3 months ago
is there another way to do it?
oh, first error is:
it looks like not work by another way to quantize model: (not support int4?)
python convert_checkpoint.py --model_dir /home/wanghaikuan/code/LLaMA-Factory/llama2-hf-lam \ --output_dir ./tllm_checkpoint_1gpu_fp16_wq \ --dtype float16 \ --use_weight_only \ --weight_only_precision int4
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 15 days."
System Info
4090
Who can help?
No response
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction
1 git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa.git 2 cd GPTQ-for-LLaMa 3 pip install -r requirements.txt 4 python llama.py ./tmp/llama/7B/ c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors ./llama-7b-4bit-gs128.safetensors
step 4 error.
Expected behavior
be able to run step 4.
actual behavior
faiure
additional notes
none