Downloads · 30 days
8
3% of all-time downloads
ConvLLaVA-JP-1.3b-768-Pretrain
toshi456/ConvLLaVA-JP-1.3b-768-Pretrain
ConvLLaVA-JP-1.3b-768-Pretrain is a text generation model from toshi456. 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.
This is a pretrained checkpoint, you can use it to instruct tune your multimodal models.
All-time downloads
286
Public
Parameters
2.1B
7.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.1 GB · 100%
Parameter types
How the weights are stored.
F321.4B · 68%
Datasets
Model card
From the Hugging Face model README
ConvLLaVA-JP Model Card
This is a pretrained checkpoint, you can use it to instruct tune your multimodal models.
Check out the instructions here
Model details
Model type: ConvLLaVA-JP is a vision-language model that can converse about input images.<br> This model is an LVLM model trained using laion/CLIP-convnext_large_d_320.laion2B-s29B-b131K-ft as the image encoder and llm-jp/llm-jp-1.3b-v1.0 as the text decoder. Supports the input of 768 x 768 high resolution images
Training dataset
Acknowledgement
License
Apache-2.0
- Task
- Text Generation
- Library
- transformers
- Type
- llava-jp
- License
- apache-2.0
- Languages
- ja
- Created
- Jun 5, 2024
- Updated
- Jun 5, 2024