Paul

Results 6 comments of Paul

albert_tiny 使用自己的数据 run_pretraining.py 问题

是和run_pretraining.py之前的 albert_tiny 模型对比的，用于ner任务的， 时间是原来的三倍，是大神你提供的albert_tiny+crf 预测执行的时间 50ms， 我使用run_pretraining.py后的模型每条数据预测时间为150ms左右

mT5 with fp16 RuntimeError: [FT][ERROR] CUDA runtime error: an illegal memory access was encountered FasterTransformer_v5.1/src/fastertransformer/utils/memory_utils.cu:96

> I am using the main branch > Can you try the latest main branch?

mT5 with fp16 RuntimeError: [FT][ERROR] CUDA runtime error: an illegal memory access was encountered FasterTransformer_v5.1/src/fastertransformer/utils/memory_utils.cu:96

> You say you use v5.1 at the beginning, do you mean that you have tested on both v5.1 and main? Sorry, I misunderstood, I tested on main not v5.1

mT5 with fp16 RuntimeError: [FT][ERROR] CUDA runtime error: an illegal memory access was encountered FasterTransformer_v5.1/src/fastertransformer/utils/memory_utils.cu:96

> I have verified and make sure the `main` branch works well. Can you > > 1. Make sure you pull the latest codes. And > 2. Provide the script...

基于Bloom和Llama的模型在同样中文指令数据上finetune，结果差异如何呢

关注

Exception when disabling "inflight_fused_batching"

I also encountered the same problem