Danni (Danqing) Zhang
                                            Danni (Danqing) Zhang
                                        
                                    Hi everyone, I also did some deep dive into the package versions of test.py file and this official package for test.py, since it reinstalled a lot of packages at the...
I also tried to add an break point here https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/training/step3_rlhf_finetuning/ppo_trainer.py#L97 and I have ``` (Pdb) tokenizer.batch_decode(seq[0:1,:]) ['\n\nHuman: Why is the Book of Enoch not always included in official Bible canon?\n\nAssistant:...
could you show me the code how you decode seq?
@nepetune233 would you mind exchanging contact information with me. My email address is [email protected]. You can send me an email. Thank you!
@nepetune233 I see, I was using the output of _generate_sequence: https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/training/step3_rlhf_finetuning/ppo_trainer.py#L68-L93
I tried to add break point in the ppo trainer code like this at first, the output is like this, and the reward is below 0 later on, after several...
Hi, you can try my script to test if your model is performing ok: https://github.com/tloen/alpaca-lora/issues/454 I also have inputs in my response when I use the generate.py file, but I...
I first had error ``` distutils.errors.DistutilsExecError: command '/opt/homebrew/bin/gcc-11' failed with exit status 1 ``` and then I run ``` brew install gcc@11 ``` but then I had error ``` gcc-11:...
Maybe try export CUDA_HOME=/usr/local/cuda-10.1/?
It looks like there is an requirement that the any dimension should be a multiply of the block size (32). Can we relax this requirement?