Downloads · 30 days
48
100% of all-time downloads
Ovis2.5-2B
ovis-community/Ovis2.5-2B
Ovis2.5-2B is a image-text-to-text model from ovis-community. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This is the community-maintained Transformers version of ATH-MaaS/Ovis2.5-2B. It provides native Ovis2.5 configuration, tokenizer, image processor, and video processor metadata so the standard Transformers Auto classe…
All-time downloads
48
Public
Parameters
2.6B
5.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.1 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- ovis2_5
- Access
- Public
- Created
- Sep 22, 2026
- Updated
- Sep 23, 2026
- SHA
- bfaa182a
Try a prompt
Base models
Model card
From the Hugging Face model README
Ovis2.5-2B
This is the community-maintained Transformers version of
ATH-MaaS/Ovis2.5-2B.
It provides native Ovis2.5 configuration, tokenizer, image processor, and video
processor metadata so the standard Transformers Auto classes can load the model
without trust_remote_code=True.
The model weights are copied unchanged from source revision
393c932b2a03e28eb9aaa503e3c4ab3ad384d958. Transformers applies the registered
Ovis2.5 weight-name mapping while loading them.
Native support is being added in huggingface/transformers#47659. Until that support is available in a Transformers release, use a checkout that contains the PR.
from transformers import AutoModelForImageTextToText, AutoProcessor
model_id = "ovis-community/Ovis2.5-2B"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
model_id,
device_map="auto",
)
Provenance
- Original checkpoint:
ATH-MaaS/Ovis2.5-2B - Original revision:
393c932b2a03e28eb9aaa503e3c4ab3ad384d958 - Weight shards, weight index, BPE vocabulary,
LICENSE, andNOTICEare copied unchanged from that revision. - Native config, processor, and tokenizer metadata are regenerated for the Transformers Ovis2.5 implementation.
Please refer to the original model card for model details, intended use, limitations, and attribution.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- ovis2_5
- License
- apache-2.0
- Created
- Sep 22, 2026
- Updated
- Sep 23, 2026