Downloads · 30 days
136
14% of all-time downloads
nano-gv
joerunde/nano-gv
nano-gv is a machine learning model from joerunde. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Random-init ~16 MB CI fixture for the sendnn-inference plugin's async multimodal-encoder tests. Generated by tools/buildnanogv.py from ibm-granite/granite-vision-3.2-2b's config.
All-time downloads
938
Public
Parameters
3.5M
20.8 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.9 MB · 67%
At a glance
- License
- apache-2.0
- Model type
- llava_next
- Access
- Public
- Created
- Jul 1, 2026
- Updated
- Jul 1, 2026
- SHA
- c9470d9e
Model card
From the Hugging Face model README
nano-gv
Random-init ~16 MB CI fixture for the sendnn-inference
plugin's async multimodal-encoder tests. Generated by tools/build_nano_gv.py
from ibm-granite/granite-vision-3.2-2b's config.
Not a functional model — outputs are meaningless. Do not use for
inference. The architecture identifiers (LlavaNextForConditionalGeneration
- granite text + siglip vision) match the source, but every dim is shrunk to the minimum that still exercises the plugin's MM code paths:
| component | source | nano |
|---|---|---|
| text hidden | 2048 | 64 |
| text layers | 40 | 2 |
| text heads | 32 | 2 |
| text head_dim | 64 | 32 |
| vision hidden | 1152 | 64 |
| vision layers | 27 | 4 |
| image size | 384 | 112 |
The tokenizer + processor are copied from the source verbatim (with
image-size fields rescaled to 112) so image_token_index and the chat
template stay valid.
- Type
- llava_next
- License
- apache-2.0
- Created
- Jul 1, 2026
- Updated
- Jul 1, 2026