metadata
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
widget:
- role: user
content:
- type: text
text: Where is this located in? What are other attractions nearby?
- type: image_url
image_url:
url: >-
https://huggingface.co/datasets/huggingface/release-assets/resolve/main/wat_arun.jpg
- role: assistant
content: >-
The image depicts the Grand Palace in Bangkok, Thailand. The Grand Palace
is a complex of buildings that served as the official residence of the
King of Siam and the administrative seat of government for 150 years. It
is one of the most popular tourist attractions in Bangkok and a must see
for anyone visiting the city. <br> Some other attractions near the Grand
Palace include: <br> * Wat Phra Kaew: This temple is located within the
Grand Palace complex and is home to the famous Emerald Buddha statue.
<br> * Wat Arum: This temple is located on the west bank of the Chao
Phraya River and is known for its stunning architecture and beautiful
views of the city. <br> * Wat Plo: This temple is located near the Grand
Palace and is home to a large reclining Buddha statue. <br> * Lump hini
Park: This park is located in the heart of Bangkok and offers a peaceful
escape from the hustle and bustle of the city. <br> * Jim Thompson House:
This museum showcases the life and work of Jim Thompson, an American
businessman who helped revitalize the Thai silk industry in the 1950 s and
1960 s. Overall, the Grand Palace is a must- see attraction in Bangkok,
and there are many other interesting places to visit in the area.
license: llama3.2
pipeline_tag: image-text-to-text
base_model: meta-llama/Llama-3.2-90B-Vision-Instruct
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- abliterated
- uncensored
huihui-ai/Llama-3.2-90B-Vision-Instruct-abliterated
This is an uncensored version of meta-llama/Llama-3.2-90B-Vision-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
It was only the text part that was processed, not the image part.