Update README.md

README.md

@@ -1,25 +1,39 @@
 ---
 base_model:
-- DavidAU/gemma-3-12b-it-heretic-R8-it-vl-polaris-alpha-1000x
+- DreamFast/gemma-3-12b-it-heretic
+- DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking
 tags:
 - text-generation-inference
 - transformers
+- unsloth
+- heretic
+- abliterated
+- uncensored
+- mergekit
+- merge
 - gemma
 - mlx
 license: apache-2.0
 language:
 - en
 datasets:
-- TeichAI/polaris-alpha-1000x
-pipeline_tag: text-generation
+- TeichAI/glm-4.7-2000x
+pipeline_tag: image-text-to-text
 library_name: mlx
 ---
 
-# gemma-3-12b-it-heretic-R8-it-vl-glm-4.7-2000x-qx86-hi-mlx
+# gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking-qx86-hi-mlx
 
-This model [gemma-3-12b-it-heretic-R8-it-vl-glm-4.7-2000x-qx86-hi-mlx](https://huggingface.co/gemma-3-12b-it-heretic-R8-it-vl-glm-4.7-2000x-qx86-hi-mlx) was
-converted to MLX format from [['DavidAU/gemma-3-12b-it-heretic-R8-it-vl-polaris-alpha-1000x']](https://huggingface.co/['DavidAU/gemma-3-12b-it-heretic-R8-it-vl-polaris-alpha-1000x'])
-using mlx-lm version **0.30.6**.
+Brainwaves
+```brainwave
+          arc   arc/e boolq hswag obkqa piqa  wino
+qx86-hi   0.585,0.756,0.874,0.724,0.462,0.798,0.717
+
+gemma-3-27b-it-heretic
+q8        0.557,0.711,0.868,0.533,0.452,0.706,0.695
+```
+
+-G
 
 ## Use with mlx
 
@@ -30,7 +44,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("gemma-3-12b-it-heretic-R8-it-vl-glm-4.7-2000x-qx86-hi-mlx")
+model, tokenizer = load("gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking-qx86-hi-mlx")
 
 prompt = "hello"
 
@@ -41,4 +55,4 @@ if tokenizer.chat_template is not None:
     )
 
 response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```
+```