Any-to-Any
Transformers
Safetensors
English
gemma4
image-text-to-text
gemma
gemma-4
quantized
int8
bitsandbytes
8-bit precision
Instructions to use dahus/gemma-4-e2b-it-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dahus/gemma-4-e2b-it-q8 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("dahus/gemma-4-e2b-it-q8") model = AutoModelForMultimodalLM.from_pretrained("dahus/gemma-4-e2b-it-q8") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 2, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 1, | |
| 106, | |
| 50 | |
| ], | |
| "pad_token_id": 0, | |
| "temperature": 1.0, | |
| "top_k": 64, | |
| "top_p": 0.95, | |
| "transformers_version": "5.6.0.dev0" | |
| } | |