Downloads · 30 days
11
19% of all-time downloads
EEVE-LLaVA-2.8B-CLIP_KO-pretrain
Nagase-Kotono/EEVE-LLaVA-2.8B-CLIP_KO-pretrain
EEVE-LLaVA-2.8B-CLIP_KO-pretrain is a text generation model from Nagase-Kotono. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
57
Public
Repo size
239 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin239 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llava_phi
- Access
- Public
- Created
- Apr 9, 2024
- Updated
- Apr 9, 2024
- SHA
- eb4a2993
Try a prompt
Model card
From the Hugging Face model README
EEVE-LLaVA-2.8B-CLIP_KO-pretrain
This model is a pretrained version of the llava multimodal projector.
You can use this model to finetune EEVE-Korean-Instruct-2.8B-v1.0 model.
Use Bingsu/clip-vit-large-patch14-ko
Hardware
3x NVIDIA A100 40GB
Software
Using MoE-LLaVA
- Task
- Text Generation
- Library
- transformers
- Type
- llava_phi
- License
- apache-2.0
- Created
- Apr 9, 2024
- Updated
- Apr 9, 2024