HF中国镜像站's logo

mlx-community
/
Forgotten-Abomination-24B-v1.2-4bit

Safetensors
English
mistral
nsfw
explicit
roleplay
unaligned
dangerous
4-bit precision
Model card Files Community
overhead520 commited on
Commit
3528210
·
verified ·
1 Parent(s): bb1aa51

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -29,6 +29,10 @@ Forgotten-Abomination-24B-v1.2 is what happens when you let two unhinged models
29
  - **GGUF Collection**:
30
  [Forgotten-Abomination-24B-v1.2](https://huggingface.co/collections/ReadyArt/forgotten-abomination-24b-v12-gguf-67b6823a28019ee3d39f1b6d)
31
 
 
 
 
 
32
  ## Recommended Settings Provided
33
 
34
  - **Mistral V7-Tekken**:
@@ -64,7 +68,7 @@ THIS MODEL WILL:
64
 
65
  ## mlx-community/Forgotten-Abomination-24B-v1.2-4bit
66
 
67
- The Model [mlx-community/Forgotten-Abomination-24B-v1.2-4bit](https://huggingface.co/mlx-community/Forgotten-Safeword-24B-4bit) was converted to MLX format from [ReadyArt/Forgotten-Abomination-24B-v1.2](https://huggingface.co/ReadyArt/Forgotten-Abomination-24B-v1.2) using mlx-lm version **0.21.1**.
68
 
69
  ## Use with mlx
70
 
 
29
  - **GGUF Collection**:
30
  [Forgotten-Abomination-24B-v1.2](https://huggingface.co/collections/ReadyArt/forgotten-abomination-24b-v12-gguf-67b6823a28019ee3d39f1b6d)
31
 
32
+ - **MLX 6bit**:
33
+ [Forgotten-Abomination-24B-v1.2-6bit](https://huggingface.co/mlx-community/Forgotten-Abomination-24B-v1.2-6bit)
34
+
35
+
36
  ## Recommended Settings Provided
37
 
38
  - **Mistral V7-Tekken**:
 
68
 
69
  ## mlx-community/Forgotten-Abomination-24B-v1.2-4bit
70
 
71
+ The Model [mlx-community/Forgotten-Abomination-24B-v1.2-4bit](https://huggingface.co/mlx-community/Forgotten-Abomination-24B-v1.2-4bit) was converted to MLX format from [ReadyArt/Forgotten-Abomination-24B-v1.2](https://huggingface.co/ReadyArt/Forgotten-Abomination-24B-v1.2) using mlx-lm version **0.21.1**.
72
 
73
  ## Use with mlx
74