Downloads · 30 days
0
Llama-2-13b-deepspeed-visualchat
AdamG012/Llama-2-13b-deepspeed-visualchat
Llama-2-13b-deepspeed-visualchat is a machine learning model from AdamG012. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Access
Public
Updated Nov 14, 2023
Repo size
30.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin30.2 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Nov 10, 2023
- Updated
- Nov 14, 2023
- SHA
- fed05032
Datasets
Model card
From the Hugging Face model README
Llama-2-13b-deepspeed-visualchat
ATTENTION: this encoder needs QwenCLIP model
DeepSpeed-VisualChat is a scalable, efficient, and user-friendly multi-modal training pipeline that leverages a novel multi-modal causal attention mechanism for better alignment of visual and text features. It uses data blending techniques to address the scarcity of interleaved text-and-image inputs in datasets.
The framework trains using a 2B visual encoder from QWen-VL and a 13B-70B language decoder from LLaMA-2, showcasing its extraordinary scalability. DeepSpeed-VisualChat is now open-sourced and encourages community contributions and collaborations. Visit the GitHub page to get started.
- License
- apache-2.0
- Languages
- en
- Created
- Nov 10, 2023
- Updated
- Nov 14, 2023