Yang Liu

Results 4 issues of Yang Liu

@KinglittleQ 你好,受限感谢分享的卓越工作,受益匪浅。 ![image](https://user-images.githubusercontent.com/14009435/64516339-ef607100-d320-11e9-8257-ffe7033e86ef.png) 有个问题请教,这里 shift 的作用是什么呢?

Thanks for the great work, here are errors from my side (one host with eight V100 GPUs): CUDA_VISIBLE_DEVICES=0 python llama_inference.py /home/xxx/models/hf_converted_llama/7B/ --wbits 4 --groupsize 128 --load llama7b-4bit-128g.pt --text "this is...

Trying to run FP16 baseline benchmark for LLaMA 30B model on a server with 8 V100 32GB GPUs: CUDA_VISIBLE_DEVICES=0,1 python llama.py /dev/shm/ly/models/hf_converted_llama/30B/ wikitext2 --benchmark 2048 --check Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████|...

3-bit quant of a 65B model, encoutered following error during pack stage: ![image](https://github.com/qwopqwop200/GPTQ-for-LLaMa/assets/14009435/3a5a961a-05a9-4210-b188-20c7a5d5f179)