Tobias van der Werff

Size 14x14 to 16x16 patch interpolation for smaller EVA 2 models

2

Hi, First of all, thank you for the great work you've published. I am trying to train EVA 2 on a custom object detection dataset and noticed that the `*_p14to16`...

[wip] SpinQuant

8

Corresponding issue: #579 This PR adds SpinQuant integration to `pytorch/ao`. See the paper for details: https://arxiv.org/abs/2405.16406. Initial results on Llama-2-7b are shown below (measured by Wikitext word perplexity). | Model...

Add SpinQuant to generate.py

2

- Add SpinQuant to `torchao/_models/llama/generate.py` - Only import SpinQuant when necessary in `eval.py` and `generate.py` (No need to import the large Hadamard matrices required for SpinQuant otherwise)

Error for Qwen2-VL-2B-Instruct using v3.0.0

2

### System Info - Ubuntu 22.04.5 - Python 3.11 - NVIDIA A100 - model: Qwen/Qwen2-VL-2B-Instruct ``` +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4 | |-----------------------------------------+------------------------+----------------------+ | GPU...

CDN URL for 4.18.0 is non-functional

7

### Is it an issue related to Adaptive Cards? No ### Is this an accessibility issue? No ### What version of Web Chat are you using? Latest production ### Which...