Update README.md
Browse files
README.md
CHANGED
@@ -8,39 +8,10 @@ tags:
|
|
8 |
- merge
|
9 |
|
10 |
---
|
11 |
-
Imatrix quants from the boi Lewdiculus <3 https://huggingface.co/Lewdiculous/Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix
|
12 |
-
|
13 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/O6REGzkSHunCzXuxsSMn7.png)
|
14 |
|
15 |
Eris with vision capabilites supported by KCPP (required for vision support): Inside Repo under mmproj-model-f16.gguf
|
16 |
|
17 |
-
|
18 |
-
|
19 |
-
### Models Merged
|
20 |
-
|
21 |
-
The following models were included in the merge:
|
22 |
-
* [InferenceIllusionist/Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b)
|
23 |
-
* [ChaoticNeutrals/Eris_Prime-V2-7B](https://huggingface.co/ChaoticNeutrals/Eris_Prime-V2-7B)
|
24 |
-
|
25 |
-
### Configuration
|
26 |
|
27 |
-
The following YAML configuration was used to produce this model:
|
28 |
|
29 |
-
```yaml
|
30 |
-
slices:
|
31 |
-
- sources:
|
32 |
-
- model: ChaoticNeutrals/Eris_Prime-V2-7B
|
33 |
-
layer_range: [0, 32]
|
34 |
-
- model: InferenceIllusionist/Excalibur-7b
|
35 |
-
layer_range: [0, 32]
|
36 |
-
merge_method: slerp
|
37 |
-
base_model: ChaoticNeutrals/Eris_Prime-V2-7B
|
38 |
-
parameters:
|
39 |
-
t:
|
40 |
-
- filter: self_attn
|
41 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
42 |
-
- filter: mlp
|
43 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
44 |
-
- value: 0.5
|
45 |
-
dtype: bfloat16
|
46 |
-
```
|
|
|
8 |
- merge
|
9 |
|
10 |
---
|
|
|
|
|
11 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/O6REGzkSHunCzXuxsSMn7.png)
|
12 |
|
13 |
Eris with vision capabilites supported by KCPP (required for vision support): Inside Repo under mmproj-model-f16.gguf
|
14 |
|
15 |
+
Imatrix quants from the boi Lewdiculus <3 https://huggingface.co/Lewdiculous/Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
|
|
17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|