Downloads · 30 days
0
libra-vision-tokenizer
YifanXu/libra-vision-tokenizer
libra-vision-tokenizer is a machine learning model from YifanXu. 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 apache-2.0.
Libra: Building Decoupled Vision System on Large Language Models
Access
Public
Updated May 17, 2024
Repo size
3.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.ckpt3.2 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- May 16, 2024
- Updated
- May 17, 2024
- SHA
- 3ea7ba79
Model card
From the Hugging Face model README
Libra Vision Tokenizer
Libra: Building Decoupled Vision System on Large Language Models
This repo provides the pretrained weight of Libra vision tokenizer trained with lookup-free quantization.
!!! NOTE !!!
-
Please merge the weights into
llama-2-7b-chat-hf-libra(huggingface version of LLaMA2-7B-Chat). -
Please download the pretrained CLIP model in huggingface and merge it into the path. The CLIP model can be downloaded here.
The files should be organized as:
llama-2-7b-chat-hf-libra/
|
│ # original llama files
|
├── ...
│
│ # newly added vision tokenizer
│
├── vision_tokenizer_config.yaml
├── vqgan.ckpt
│
│ # CLIP model
│
└── openai-clip-vit-large-patch14-336/
└── ...
- License
- apache-2.0
- Created
- May 16, 2024
- Updated
- May 17, 2024