Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
|
|
|
|
|
| 1 |
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.
|
| 2 |
|
| 3 |
|
|
|
|
| 1 |
+
# Llama-2-13b-deepspeed-visualchat
|
| 2 |
+
|
| 3 |
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.
|
| 4 |
|
| 5 |
|