Downloads · 30 days
311
15% of all-time downloads
edp1096/Huihui-gemma-4-E2B-it-abliterated-litert-lm
Huihui-gemma-4-E2B-it-abliterated-litert-lm is a image-text-to-text model from edp1096. 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 litert-lm. The card lists the license as apache-2.0.
Multimodal LiteRT-LM conversion of huihui-ai/Huihui-gemma-4-E2B-it-abliterated.
Downloads · 30 days
311
15% of all-time downloads
All-time downloads
2.1K
Public
Repo size
5.2 GB
Likes
3
Public
Click a slice to open those files.
.litertlm5.2 GB · 100%
From the Hugging Face model README
Multimodal LiteRT-LM conversion of
huihui-ai/Huihui-gemma-4-E2B-it-abliterated.
The bundle contains INT8 text prefill/decode, external and per-layer embedders, a Gemma 4 vision encoder, and a vision adapter. It was converted natively on a Linux ARM64 NVIDIA DGX Spark; no x86 emulation was used.
image_text_to_textdynamic_wi8_afp32 for text and visionlitert-lm import \
Huihui-gemma-4-E2B-it-abliterated.litertlm \
huihui-gemma4-e2b
litert-lm run huihui-gemma4-e2b \
--backend gpu \
--vision-backend gpu \
--attachment image.png \
--prompt "Describe this image."
The resulting bundle is approximately 4.9 GiB. Text and image inference were both validated through the LiteRT-LM CLI and its OpenAI-compatible API.
The source is an abliterated model with substantially reduced refusal behavior. It can produce sensitive, controversial, or inappropriate content. Review its outputs and do not assume that it provides default safety guarantees.