Instructions to use huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated") model = AutoModelForMultimodalLM.from_pretrained("huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ This is a crude, proof-of-concept implementation to remove refusals from an LLM
|
|
| 20 |
|
| 21 |
Please use the latest version of [ollama](https://github.com/ollama/ollama/releases/)
|
| 22 |
|
| 23 |
-
You can use [huihui_ai/gemma-4-abliterated:26b-qat](https://ollama.com/huihui_ai/gemma-4-abliterated:
|
| 24 |
```
|
| 25 |
ollama run huihui_ai/gemma-4-abliterated:26b-qat
|
| 26 |
```
|
|
|
|
| 20 |
|
| 21 |
Please use the latest version of [ollama](https://github.com/ollama/ollama/releases/)
|
| 22 |
|
| 23 |
+
You can use [huihui_ai/gemma-4-abliterated:26b-qat](https://ollama.com/huihui_ai/gemma-4-abliterated:26b-qat) directly,
|
| 24 |
```
|
| 25 |
ollama run huihui_ai/gemma-4-abliterated:26b-qat
|
| 26 |
```
|