dynamix

Re:Towards Optimal LLM Quantization on Thursday May 30, 2024 @02:03PM (#40526781)

Is there a way for me to compress a custom fine-tuned model of my own?

On-Device LLM Inference Powered by X-Bit Quantization

Posted by dynamix on Wednesday May 29, 2024 @10:29AM
from the github.com dept.

( Read More... | no comments | 13 points | on HN )

Re:Show HN: Whisper and ChatGPT and ElevenLabs on Raspberry Pi on Friday June 02, 2023 @02:30PM (#36168944)

try `chat G P T`

Posted by dynamix on Friday December 23, 2022 @02:48PM
from the picovoice.ai dept.

( Read More... | no comments | 3 points | on HN )

Posted by dynamix on Friday April 29, 2022 @11:18AM
from the medium.com dept.

( Read More... | no comments | 5 points | on HN )

Posted by dynamix on Thursday March 17, 2022 @12:36PM
from the github.com dept.

( Read More... | no comments | on HN )

Posted by dynamix on Tuesday March 16, 2021 @11:28AM
from the medium.com dept.

( Read More... | no comments | 5 points | on HN )