罗皓天 (Haotian Luo)

When eval the model on amazon datasets, the result fluctuate.

1

Hi @rktamplayo , thank you for your great work! I followed the README.md to reproduce the experimental results on Amazon dataset and use the check point you released to evaluate...

A typo on paper

1

Hi Brcsomnath, I find that in your paper the Table 5 has a typo: the PMR should be Acc, right? This may lead to some misunderstanding.

Need help with the method of connecting self RL agent to showdown

1

Following the tutorial, I've trained my agent in DQN(in fact I modified it to D3QN by adding parameter enable_dueling_network=True). Then I got the model.summary(): _________________________________________________________________ Layer (type) Output Shape Param...

Too slow training

2

Hi, @hsahovic . I'm recently playing with the project. I've noticed that in the docs [doc](https://poke-env.readthedocs.io/en/stable/rl_with_open_ai_gym_wrapper.html?highlight=placement_battles#use-provided-evaluate-player-method) you said the code can be finished in 5 minutes but in fact on...

When training on nips dataset, my performance get stuck at around acc of 54%, much less than the result in the paper. I want to now how can I improve...

Hi, I'm recently doing some survey on math model. And I found that seems the result you reported on WizardMath is by zero-shot "let's think step by step"? (For MATH...

the inference of OFA-Sys/gsm8k-rft-llama13b2-u13b has shape error: 13Bllama2的u13b版本推理时出现矩阵形状错误

8

There seems no people tried your 13b2-u13b version and I may be the first one. But I got 'RuntimeError: mat1 and mat2 shapes cannot be multiplied (111x5120 and 1x2560)' on...

Permission denied on file system

1

When I do restore or backup, AppIndex would warn that don't have permission. I'm with iOS 14.2 unc0ver.