Downloads · 30 days
12
4% of all-time downloads
Algea-VE
PhelixZhen/Algea-VE
Algea-VE is a visual question answering model from PhelixZhen. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Algea-ve is trained on the LAION-CC-SBU dataset using algea-550M-base as the base model and fine-tuned on llavav15mix665k. It uses CLIP ViT-L/14-336 as the visual encoder. The model is very small, requiring only 32GB…
All-time downloads
296
Public
Parameters
862M
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 99%
At a glance
- Task
- Visual Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- mipha_phi
- Access
- Public
- Created
- Jun 9, 2024
- Updated
- Jun 10, 2024
- SHA
- ac4fe074
Model card
From the Hugging Face model README
Algea-VE: A Tiny Multimodal Language Model with Only 0.8B Parameters
Algea-ve is trained on the LAION-CC-SBU dataset using algea-550M-base as the base model and fine-tuned on llava_v1_5_mix665k. It uses CLIP ViT-L/14-336 as the visual encoder. The model is very small, requiring only 32GB of VRAM for fine-tuning and 3GB for inference.
Due to insufficient training of the base model, the current model has some issues with hallucinations and repetition. To address this, I am training a new model that will maintain the same size but offer better performance.
This model is built based on the llavaphi project. To use the model, please click here.
- Task
- Visual Question Answering
- Library
- transformers
- Type
- mipha_phi
- License
- apache-2.0
- Languages
- en
- Created
- Jun 9, 2024
- Updated
- Jun 10, 2024