Horacio Vico

ROG Zephyrus GX501 support

6

Hi, Are there any plans to support the ASUS ROG Zephyrus GX501? It has one of this numpads. I offer mine to do testing or checks if it is required....

Error on GTX 1080 Maq-Q

2

Hi! Trying to finetune a Mistral 7B v0.2 on my GTX 1080 Max-q. Getting this error (using LLaMA Factory): ==((====))== Unsloth: Fast Mistral patching release 2024.4 \\ /| GPU: NVIDIA...

Hello, Could you provide an INT8 calibration file in order to run this fd_lpd.caffemodel in DeepStream 5 with better performance? Thanks

Hello, I'm trying to export this model and its weights into a frozen graph. So far I did this in the "save images" part of the training loop: saver =...

Finetuning example loss does not decrease over time

8

### System Info / 系統信息 CUDA 12.1, Torch 2.3 ### Who can help? / 谁可以帮助到您？ _No response_ ### Information / 问题信息 - [ ] The official example scripts / 官方的示例脚本...

ipex Llama.cpp server fails with Phi3 models

2

Hi, I've trying to serve different Phi3 models using the Llama.cpp server that is created by the init-llama-cpp ipex. When I server with this version I have two problems: 1)...