Downloads · 30 days
11
31% of all-time downloads
llavanext-v1.5-0.5b
henrywch2huggingface/llavanext-v1.5-0.5b
llavanext-v1.5-0.5b is a image-to-text model from henrywch2huggingface. Use it when you need a caption or text from an image. The card lists the license as apache-2.0.
:::important[NOTICE]As the training scripts was mis-selected (LLaVA-NeXT/scripts/train/pretrainclip.sh + LLaVA-NeXT/scripts/train/directfinetuneclip.sh), the model cannot align with LLaVAOneVision Class in opencompass…
All-time downloads
36
Public
Parameters
799M
1.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 99%
At a glance
- Task
- Image-to-Text
- License
- apache-2.0
- Model type
- llava_qwen
- Access
- Public
- Created
- Aug 3, 2025
- Updated
- Aug 7, 2025
- SHA
- bad79d63
Base models
Model card
From the Hugging Face model README
:::important[NOTICE]As the training scripts was mis-selected (LLaVA-NeXT/scripts/train/pretrain_clip.sh + LLaVA-NeXT/scripts/train/direct_finetune_clip.sh), the model cannot align with LLaVA_OneVision Class in opencompass/VLMEvalKit. Please redirect to henrywch2huggingface/llavanext-scaled-0.5b.:::
- Task
- Image-to-Text
- Type
- llava_qwen
- License
- apache-2.0
- Created
- Aug 3, 2025
- Updated
- Aug 7, 2025