robotsp

Env: spark standalone on docker Case: the trained pyspark model (randomforest) deployed on docker Questions: When I use gunicorn to start the service, including (model loading, prediction) and expose API...

The docker is deployed with spark standalone, and load the trained pyspark model (randomforest). But when I use gunicorn to start it up, it is very slow and give prediction....

Is there any method can be used to prune translation model in fairseq?

8

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### What is your question? #### Code #### What have you tried? #### What's...

I implemented a function in fairseq_cli/train.py, to freeze the parameters, ``` def freeze_param_grad_zero(model): for name, param in model.named_parameters(): if "fc1" in name or "fc2" in name: print("========= start freezing =========")...

How can I save the checkpoint, of which the weights has been altered?

27

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### What is your question? #### Code #### What have you tried? #### What's...

账号是通过手机验证码登陆的，如何修改cookie json文件进行导出？

1

@DeppWang 请教一下大佬们

@Glaceon31 Thank you in advance!

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### What is your question? #### Code #### What have you tried? #### What's...

@LeslieOverfitting , Would you please share which code files did you develop, I have found `selective_distillation/tree/main/fairseq/criterions/label_smoothed_cross_entropy.py` is the one that you develop the distillation strategy. What else? Thanks!

How did you reproduce the experimental results of baselines?

1

@FadedCosine Hi, would you please provide the code of reproducing the experimental results of baselines (Word-KD, Seq-KD, and BERT-KD) in Table 2 of your paper? Many thanks!