Nitral-AI commited on
Commit
e57a15e
1 Parent(s): 0ed919b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -23
README.md CHANGED
@@ -9,30 +9,16 @@ tags:
9
 
10
  ---
11
 
 
12
 
13
- The following models were included in the merge:
14
- * [Nitral-AI/Lelemon-Maid-7B](https://huggingface.co/Nitral-AI/Lelemon-Maid-7B)
15
- * [Nitral-AI/KukulStanta-7B](https://huggingface.co/Nitral-AI/KukulStanta-7B)
16
 
17
- ### Configuration
18
 
19
- The following YAML configuration was used to produce this model:
 
 
 
 
20
 
21
- ```yaml
22
- slices:
23
- - sources:
24
- - model: Nitral-AI/Lelemon-Maid-7B
25
- layer_range: [0, 32]
26
- - model: Nitral-AI/KukulStanta-7B
27
- layer_range: [0, 32]
28
- merge_method: slerp
29
- base_model: Nitral-AI/Lelemon-Maid-7B
30
- parameters:
31
- t:
32
- - filter: self_attn
33
- value: [0, 0.5, 0.3, 0.7, 1]
34
- - filter: mlp
35
- value: [1, 0.5, 0.7, 0.3, 0]
36
- - value: 0.5
37
- dtype: bfloat16
38
- ```
 
9
 
10
  ---
11
 
12
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/pQ5xEj4JOyNF_dvBkuIa6.png)
13
 
14
+ # Vision/multimodal capabilities:
 
 
15
 
16
+ If you want to use vision functionality:
17
 
18
+ * You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
19
+
20
+ To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo.
21
+
22
+ * You can load the **mmproj** by using the corresponding section in the interface:
23
 
24
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)