puja93

Results 5 comments of puja93

Set correct compile flags for Apple M1 chips as well as 32bit machines.

Thanks @tmikus , your PR works fine on my M1 for utf-8 but not byte object, as you mentioned. It has been sometime, but i do wonder if you've found...

[1] 7092 segmentation fault python - Error is coming

Same issue

How can I convert llama3 safetensors to the pth file needed to use with executorch?

Hey @kartikayk, do you know if torchtune can also convert the quantized version of llama3 safetensors back to .pth ? As you see, every mlp or attention, expanded to have...

Llama Architecture for Quantized Checkpoint (GPTQ)

Its gptq... I didnt quantize the model, its in one of Huggingface repo..

PySR paper is out!

Hi @MilesCranmer... Thanks for the great paper and repo. Regarding the 8th point in your paper : Do you have any links for documentation or tutorial on that ? Especially...