Update README.md

README.md

@@ -3,23 +3,30 @@ license: gemma
 base_model:
 - google/gemma-3-27b-it
 - nidum/Nidum-gemma-3-27B-it-Uncensored
+base_model_relation: quantized
 pipeline_tag: image-text-to-text
 tags:
 - chat
 - mlx
 - uncensored
+- gemma3
 - apple
 - 4bit
+language:
+- en
+- fr
+- es
+- de
+- it
+- hi
+- ru
 library_name: mlx
 ---
 
 # Gemma-3-27B Instruct Uncensored 4-bit MLX
 Uncensored version of **Gemma 3 27B**.
 
-This model was converted to MLX format from [`nidum/Nidum-gemma-3-27B-it-Uncensored`]() using mlx-vlm version **0.1.19**.
-
-Refer to the [original model card](https://huggingface.co/google/gemma-3-27b-it) and [uncensored model](https://huggingface.co/nidum/Nidum-gemma-3-27B-it-Uncensored) for more details on the model.
-
+Also you can try new uncensored version: [Amoral Gemma-3 27B 4-bit MLX](https://huggingface.co/TheCluster/amoral-gemma-3-27B-v2-mlx-4bit)
 
 ## Technical Details
 
@@ -27,6 +34,8 @@ Supports a context length of 128k tokens, with a max output of 8192.
 
 Multimodal supporting images normalized to 896 x 896 resolution.
 
+Refer to the [original model card](https://huggingface.co/google/gemma-3-27b-it) and [uncensored model](https://huggingface.co/nidum/Nidum-gemma-3-27B-it-Uncensored) for more details on the model.
+
 
 ## Use with mlx
 
@@ -35,5 +44,8 @@ pip install -U mlx-vlm
 ```
 
 ```bash
-python -m mlx_vlm.generate --model TheCluster/gemma-3-27b-it-uncensored-mlx-4bit --max-tokens 128 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
-```
+python -m mlx_vlm.generate --model TheCluster/gemma-3-27b-it-uncensored-mlx-4bit --max-tokens 256 --temperature 0.4 --prompt "Describe this image." --image <path_to_image>
+```
+
+### Source
+This model was converted to MLX format from [`nidum/Nidum-gemma-3-27B-it-Uncensored`](https://huggingface.co/nidum/Nidum-Gemma-3-27B-it-Uncensored) using mlx-vlm version **0.1.19**.