Commit
·
776a6e6
1
Parent(s):
8c21813
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,7 @@ datasets:
|
|
| 10 |
[Blog post]() | [Code](https://github.com/mlfoundations/open_flamingo) | [Demo](https://7164d2142d11.ngrok.app)
|
| 11 |
|
| 12 |
OpenFlamingo is an open source implementation of DeepMind's [Flamingo](https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model) models.
|
| 13 |
-
OpenFlamingo-9B is built off of [CLIP ViT-L/14](https://huggingface.co/openai/clip-vit-large-patch14) and [LLaMA-7B](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/).
|
| 14 |
-
|
| 15 |
|
| 16 |
## Model Details
|
| 17 |
We freeze the pretrained vision encoder and language model, and then we train connecting Perceiver modules and cross-attention layers, following the original Flamingo paper.
|
|
|
|
| 10 |
[Blog post]() | [Code](https://github.com/mlfoundations/open_flamingo) | [Demo](https://7164d2142d11.ngrok.app)
|
| 11 |
|
| 12 |
OpenFlamingo is an open source implementation of DeepMind's [Flamingo](https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model) models.
|
| 13 |
+
OpenFlamingo-9B is built off of [CLIP ViT-L/14](https://huggingface.co/openai/clip-vit-large-patch14) and [LLaMA-7B](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/). Before using this model please familiarize yourself with our [terms and conditions](https://github.com/mlfoundations/open_flamingo/blob/main/TERMS_AND_CONDITIONS.md).
|
|
|
|
| 14 |
|
| 15 |
## Model Details
|
| 16 |
We freeze the pretrained vision encoder and language model, and then we train connecting Perceiver modules and cross-attention layers, following the original Flamingo paper.
|