turing-motors
/

Heron-NVILA-Lite-1B

Image-Text-to-Text

Model card Files Files and versions

chantera commited on Oct 20

Commit

a9a7070

·

verified ·

1 Parent(s): e5c54e7

Update README.md

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -13,7 +13,11 @@ base_model:
 - Qwen/Qwen2.5-0.5B-Instruct
 - Efficient-Large-Model/paligemma-siglip-so400m-patch14-448
 pipeline_tag: image-text-to-text
 ---
 # Heron-NVILA-Lite-1B
 Heron-NVILA-Lite-1B is a vision language model trained for Japanese, based on the [NVILA](https://arxiv.org/abs/2412.04468)-Lite architecture.

 - Qwen/Qwen2.5-0.5B-Instruct
 - Efficient-Large-Model/paligemma-siglip-so400m-patch14-448
 pipeline_tag: image-text-to-text
+new_version: turing-motors/Heron-NVILA-Lite-1B-hf
 ---
+> [!NOTE]
+> We have released [Heron-NVILA-Lite-1B-hf](https://huggingface.co/turing-motors/Heron-NVILA-Lite-1B-hf), an implementation compatible with `transformers.AutoModelForImageTextToText`.
 # Heron-NVILA-Lite-1B
 Heron-NVILA-Lite-1B is a vision language model trained for Japanese, based on the [NVILA](https://arxiv.org/abs/2412.04468)-Lite architecture.