OmnicromsBrain commited on
Commit
fbe296d
1 Parent(s): b2fc576

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -7
README.md CHANGED
@@ -29,6 +29,18 @@ NeuralStar_FusionWriter_4x7b is a Mixture of Experts (MoE) made with the followi
29
  * [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
30
  * [OmnicromsBrain/NeuralStar_Fusion-7B](https://huggingface.co/OmnicromsBrain/NeuralStar_Fusion-7B)
31
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  ## 🧩 Configuration
33
 
34
  ```yaml
@@ -40,7 +52,7 @@ experts:
40
  - "assistant"
41
  - "tell me"
42
  - "explain"
43
- - "Ideas"
44
  - source_model: OmnicromsBrain/Eros_Scribe-7b
45
  positive_prompts:
46
  - "adult"
@@ -63,13 +75,7 @@ experts:
63
  - "scenebeat"
64
  - "prose"
65
  ```
66
- ## ⚡ Quantized Models
67
 
68
- Special thanks to MRadermacher for the static and weighted/imatrix quantsquantized models
69
-
70
- **.GGUF** https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF
71
-
72
- **IMatrix** https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-i1-GGUF
73
 
74
 
75
  ## 💻 Usage
 
29
  * [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
30
  * [OmnicromsBrain/NeuralStar_Fusion-7B](https://huggingface.co/OmnicromsBrain/NeuralStar_Fusion-7B)
31
 
32
+
33
+
34
+ ## ⚡ Quantized Models
35
+
36
+ Special thanks to **MRadermacher** for the **static** and **imatrix** quantized models
37
+
38
+ **.GGUF** https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-GGUF
39
+
40
+ **IMatrix** https://huggingface.co/mradermacher/NeuralStar_FusionWriter_4x7b-i1-GGUF
41
+
42
+
43
+
44
  ## 🧩 Configuration
45
 
46
  ```yaml
 
52
  - "assistant"
53
  - "tell me"
54
  - "explain"
55
+ - "ideas"
56
  - source_model: OmnicromsBrain/Eros_Scribe-7b
57
  positive_prompts:
58
  - "adult"
 
75
  - "scenebeat"
76
  - "prose"
77
  ```
 
78
 
 
 
 
 
 
79
 
80
 
81
  ## 💻 Usage