Downloads · 30 days
15
10% of all-time downloads
Gemma3NPC-filtered
chimbiwide/Gemma3NPC-filtered
Gemma3NPC-filtered is a image-text-to-text model from chimbiwide. 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.
We trained this model as a rank-12 LoRA adapter with one epoch over pippafiltered using a 40GB vRAM A100 in Google Colab. For this run, we employed a learning rate of 2e-5 and a total batch size of 1 and gradient accu…
All-time downloads
155
Public
Parameters
8.4B
15.7 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors15.7 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- gemma3n
- Access
- Public
- Created
- Aug 5, 2025
- Updated
- Aug 14, 2025
- SHA
- eb3399f6
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Gemma3NPC-filtered-float16
The "filtered" model that delivers censored general role-playing at great speed.
We trained this model as a rank-12 LoRA adapter with one epoch over pippa_filtered using a 40GB vRAM A100 in Google Colab. For this run, we employed a learning rate of 2e-5 and a total batch size of 1 and gradient accumulation steps of 16. A cosine learning rate scheduler was used with a 150-step warmup. With a gradient clipping of 0.5.
Check out our training notebook here.
Here is a graph of the Step Training Loss, saved every 5 steps:
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma3n
- License
- apache-2.0
- Languages
- en
- Created
- Aug 5, 2025
- Updated
- Aug 14, 2025