Downloads · 30 days
90
2% of all-time downloads
KoLLaVA-KoVicuna-7b
tabtoyou/KoLLaVA-KoVicuna-7b
KoLLaVA-KoVicuna-7b is a text generation model from tabtoyou. 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 model is a large multimodal model (LMM) that combines the LLM(KoVicuna) with visual encoder of CLIP(ViT-14), trained on Korean visual-instruction dataset.
All-time downloads
5.2K
Public
Repo size
53.9 GB
Likes
13
Public
Repo makeup
Click a slice to open those files.
.bin27 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llava
- Access
- Public
- Created
- Jun 12, 2023
- Updated
- Jun 25, 2023
- SHA
- 025a479b
Model card
From the Hugging Face model README
KoLLaVA : Korean Large Language and Vision Assistant (feat. LLaVA)
This model is a large multimodal model (LMM) that combines the LLM(KoVicuna) with visual encoder of CLIP(ViT-14), trained on Korean visual-instruction dataset.
Detail codes are available at KoLLaVA github repository
Training hyperparameters
- learning rate : 2e-5
- train_batch_size: 16
- distributed_type: multi-GPU (A100 80G)
- num_devices: 4
- gradient_accumulation_steps: 1
- total_train_batch_size: 64
- total_eval_batch_size: 16
- lr_scheduler_type: cosine
- num_epochs: 1
Model License: Apache License 2.0
- Task
- Text Generation
- Library
- transformers
- Type
- llava
- License
- apache-2.0
- Languages
- ko
- Created
- Jun 12, 2023
- Updated
- Jun 25, 2023