Jiarui Fang（方佳瑞）
Jiarui Fang（方佳瑞）
Thanks yufeng, Could you please give me some references on quantization?
sys.argv[0] 是 "convert_tf_bert_to_npz.py ", sys.argv[1] 才是你的模型= =
市面上有很多脚本把tf 1.0可以转化为2.0 另外非huggingface的tf模型载入可以参考 #13
No, we use FP32.
Interesting. Feedbacks from our customers indicate our FP32 version is fast enough. We believe quantization on CPU is more intensive, therefore we currently have no plan for GPU FP16. We...
Did huggingface's decoder work for you?
So, your code works when using opennmt, but is failed after switching to turbo?
It looks that you are using turbo correctly. It *maybe* some bad cases in Turbo decoder. Can you run OpenNMT decoder and Turbo simultaneously? And check the results of two...
Did you see the Device memory usage? The crush may result from excessive GPU memory consumption. ` nvidia-smi --id=0 --query-compute-apps=used_memory --format=csv -lms 100 `
I have some hints for you to debug. 1. use CPU only to check if the results are always the same with ONMT. 2. Try to upgrade your PyTorch version...