KumarGitesh2024 comments

Results 6 comments of


                                            KumarGitesh2024

AVX2 is dimwitted compared to AVX512

Hi @jart Thank you for the confirmation, hence closing this issue.

Mismatch between expected 1024000 and actual 1024512 KiB size.

Hi @ticcky , Could you please confirm, if the issue is resolved. If yes, please feel free to move this issue to closed status

Gemma.cpp hangs on a Gemma 7B model that was finetuned using huggingface peft(QLoRA)

Hi @webbigdata-jp, Can you share logs after printing the function using `cout` to understand which function in **gemma.cc** is producing issues or waiting to respond?

Can we use gemma.cpp as a library in Android APP?

Hi @FranzKafkaYu , Have you tried the guided steps, is issue resolved? If yes, please feel free to move this issue to closed status.

Update casesensitivity in fine_tuning_tutorial.ipynb

Hi @Gopi-Uppari , I have shared you the access.

Update casesensitivity in fine_tuning_tutorial.ipynb

Hi @Gopi-Uppari, I have updated the link for the gist which you shared. [gist](https://colab.research.google.com/gist/Gopi-Uppari/94761786ea93167498922d573c6581fc/updating-casesensitivity-issue-in-gsm8k_eval.ipynb)