empty2enrich comments

Results 8 comments of


                                            empty2enrich

error: invalid static_cast from type ‘const torch::OrderedDict<std::basic_string<char>, at::Tensor>’ to type ‘torch::OrderedDict<std::basic_string<char>, at::Tensor>&’

> @cicirori is right. Resetting to `f3a960f`can complete the installation but causes another bug when importing. Did you solve the import problem?

下载文件时去了还未成功同步的 storage 上下载，tracker.conf 配置了 download_server=1

使用了 ha 对 tracker 负载

下载文件时去了还未成功同步的 storage 上下载，tracker.conf 配置了 download_server=1

两套 fastdfs 服务器时间是一致的

I trained myself, but I can't achieve the effect of the paper

trained on the 300W-LP dataset., test on the ALFW2000

I trained myself, but I can't achieve the effect of the paper

I don't understand very well, I used the source code for training without modification. Why do I need to check the data？ thank you for your reply！

Error deploying docker on P3 instance

> I think if you use Llama it might work. I was able to make it work on V100 gpus I use v100, also encountered problems， log: ``` ... 2023-09-06T03:45:33.105882Z...

[Question]: parsing is very slow and basically unavailable, the advantages of the model are hard to perceive

> We're working on accelerating parsing speed。 And parsing is slow partly because text embedding is processing at the same time. It's gona be realy slow if you're using CPU....

求教：模型输出结果不完整问题。

> config里的参数用的是默认的吗？可以给具体的例子吗使用的 baichuan2 默认配置