Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
# Model Card for Model ID
|
| 5 |
+
|
| 6 |
+
Model in paper Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference. Finetuned from mamba-based language models.
|
| 7 |
+
|
| 8 |
+
## Model Details
|
| 9 |
+
|
| 10 |
+
This is a multi-modal large language model that takes one image and text prompt as inputs and outputs text answers.
|
| 11 |
+
|
| 12 |
+
### Model Sources [optional]
|
| 13 |
+
|
| 14 |
+
<!-- Provide the basic links for the model. -->
|
| 15 |
+
|
| 16 |
+
- **Repository:** https://github.com/h-zhao1997/cobra
|
| 17 |
+
- **Paper [optional]:** https://arxiv.org/abs/2403.14520
|
| 18 |
+
- **Demo [optional]:** https://huggingface.co/spaces/han1997/cobra
|
| 19 |
+
|