Aller au contenu
ModelPrésentéExterne
Télécharger

Algea VE

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...

Sourcehuggingface.co/PhelixZhen/Algea-VE/tree/ac4fe074ba485928daf344a8ff7c812d4029016a
TypeText modelVersionmodelBClasse

Source du modèle

Type
Text model
Taille du fichier
1,60 GB
Version
vmodel
Mis à jour
22 sept. 2026
Téléchargements
16
Source
Hugging Face

Description de la source

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.

Sources

1 source
Hugging FacePrincipalVersion ac4fe074ba485928daf344a8ff7c812d4029016a
huggingface.co/PhelixZhen/Algea-VE/tree/ac4fe074ba485928daf344a8ff7c812d4029016a

Vérifié 28 août

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 1,60 GB · SHA-256 9e7305603226…faf9 · Hugging Face

Download file

Extraits de sources

2 extraits
Readme28 aoûthuggingface.co/PhelixZhen/Algea-VE

--- license: apache-2.0 language: - en pipeline_tag: visual-question-answering --- # 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](https://huggingface.co/PhelixZhen/Algae-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](https://github.com/phelixzhen/Algea-VE).

Note28 aoûthuggingface.co/PhelixZhen/Algea-VE

Source context: 16 downloads · 0 likes · Pipeline visual-question-answering · Library transformers · Repo PhelixZhen/Algea-VE