Add arxiv link
Browse filesWill link the model to paper pages
README.md
CHANGED
@@ -1,13 +1,15 @@
|
|
|
|
|
|
|
|
1 |
# Med-Flamingo-9B (CLIP ViT-L/14, Llama-7B)
|
2 |
|
3 |
![](logo.png)
|
4 |
|
5 |
-
Med-Flamingo is a medical vision-language model with multimodal in-context learning abilities.
|
6 |
|
7 |
This model is based on the OpenFlamingo-9B V1 model which uses the CLIP ViT-L/14 vision encoder and the Llama-7B language model as frozen backbones.
|
8 |
|
9 |
Med-Flamingo was trained on paired and interleaved image-text from the medical literature.
|
10 |
|
11 |
|
12 |
-
Check out our [git repo](https://github.com/snap-stanford/med-flamingo) for more details on setup & demo.
|
13 |
-
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
# Med-Flamingo-9B (CLIP ViT-L/14, Llama-7B)
|
5 |
|
6 |
![](logo.png)
|
7 |
|
8 |
+
[Med-Flamingo](https://arxiv.org/abs/2307.15189) is a medical vision-language model with multimodal in-context learning abilities.
|
9 |
|
10 |
This model is based on the OpenFlamingo-9B V1 model which uses the CLIP ViT-L/14 vision encoder and the Llama-7B language model as frozen backbones.
|
11 |
|
12 |
Med-Flamingo was trained on paired and interleaved image-text from the medical literature.
|
13 |
|
14 |
|
15 |
+
Check out our [git repo](https://github.com/snap-stanford/med-flamingo) for more details on setup & demo.
|
|