Downloads · 30 days
12
0% of all-time downloads
grimulkan/Llama-3.2-90B-Vision-Hermes-3-lorablated-merge
Llama-3.2-90B-Vision-Hermes-3-lorablated-merge is a machine learning model from grimulkan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.2.
This is a merge of the vision adapters from meta-llama/Llama-3.2-90B-Vision-Instruct onto mlabonne/Hermes-3-Llama-3.1-70B-lorablated.
Downloads · 30 days
12
0% of all-time downloads
All-time downloads
7.3K
Public
Parameters
88.6B
177 GB on disk
Likes
5
Public
Click a slice to open those files.
.safetensors177 GB · 100%
From the Hugging Face model README
This is a merge of the vision adapters from meta-llama/Llama-3.2-90B-Vision-Instruct onto mlabonne/Hermes-3-Llama-3.1-70B-lorablated.
Please respect the respective licenses of Meta Llama & Nous Research.
The method I used is detailed in this post. I also merged the tokenizer and generation configs. Example python code for weight merging is available in merge_vision_example.py, which works for both 11B and 90B.
An 11B version of this merge is available here.