VictorSanh
commited on
Commit
•
bc7e459
1
Parent(s):
6e13295
being explicit with transformers version
Browse files
README.md
CHANGED
@@ -38,8 +38,9 @@ Idefics2 is an open multimodal model that accepts arbitrary sequences of image a
|
|
38 |
We release under the Apache 2.0 license 2 checkpoints:
|
39 |
- [idefics2-8b-base](https://huggingface.co/HuggingFaceM4/idefics2-8b-base): the base model
|
40 |
- [idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b): the base model fine-tuned on a mixture of supervised and instruction datasets (text-only and multimodal datasets)
|
41 |
-
- idefics2-8b-chatty (coming soon): `idefics2-8b` further fine-tuned on long
|
42 |
|
|
|
43 |
|
44 |
# Model Summary
|
45 |
|
|
|
38 |
We release under the Apache 2.0 license 2 checkpoints:
|
39 |
- [idefics2-8b-base](https://huggingface.co/HuggingFaceM4/idefics2-8b-base): the base model
|
40 |
- [idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b): the base model fine-tuned on a mixture of supervised and instruction datasets (text-only and multimodal datasets)
|
41 |
+
- idefics2-8b-chatty (coming soon): `idefics2-8b` further fine-tuned on long conservation
|
42 |
|
43 |
+
**As of April 15th, 2024**, Idefics2 is not part of a Transformers pypi release. Please install Transformers from `main` (for instance with `pip install -q git+https://github.com/huggingface/transformers`).
|
44 |
|
45 |
# Model Summary
|
46 |
|