Downloads · 30 days
10
14% of all-time downloads
peerbench/gemma-4-E4B-20260610190427-v2
gemma-4-E4B-20260610190427-v2 is a image-text-to-text model from peerbench. 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 gemma.
Fine-tuned unsloth/gemma-4-E4B-it on a curated, native-heavy German SFT corpus to improve general German skill (not a single benchmark). SFT · LoRA · bf16 · reasoning OFF.
Downloads · 30 days
10
14% of all-time downloads
All-time downloads
70
Public
Parameters
8B
16 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16 GB · 100%
From the Hugging Face model README
Fine-tuned unsloth/gemma-4-E4B-it on a curated, native-heavy German SFT corpus to improve general German skill (not a single benchmark). SFT · LoRA · bf16 · reasoning OFF.
Variant: v2
gemma4-de-v2) — 25756 rowsgaa-mdk (entity forest-wb), run gemma-4-E4B-v2__sftmix-r128__20260610190427 · date_utc 20260610190427