remove additional details not relating to AWQ
Browse files
README.md
CHANGED
@@ -59,29 +59,6 @@ The following models were included in the merge:
|
|
59 |
* [NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story](https://huggingface.co/NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story)
|
60 |
* [NeuralNovel/Gecko-7B-v0.1-DPO](https://huggingface.co/NeuralNovel/Gecko-7B-v0.1-DPO)
|
61 |
|
62 |
-

|
63 |
-
|
64 |
-
The following YAML configuration was used to produce this model:
|
65 |
-
|
66 |
-
```yaml
|
67 |
-
|
68 |
-
slices:
|
69 |
-
- sources:
|
70 |
-
- model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
|
71 |
-
layer_range: [0, 32]
|
72 |
-
- model: NeuralNovel/Gecko-7B-v0.1-DPO
|
73 |
-
layer_range: [0, 32]
|
74 |
-
merge_method: slerp
|
75 |
-
base_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
|
76 |
-
parameters:
|
77 |
-
t:
|
78 |
-
- filter: self_attn
|
79 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
80 |
-
- filter: mlp
|
81 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
82 |
-
- value: 0.5
|
83 |
-
dtype: bfloat16
|
84 |
-
|
85 |
## How to use
|
86 |
|
87 |
### Install the necessary packages
|
|
|
59 |
* [NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story](https://huggingface.co/NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story)
|
60 |
* [NeuralNovel/Gecko-7B-v0.1-DPO](https://huggingface.co/NeuralNovel/Gecko-7B-v0.1-DPO)
|
61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
## How to use
|
63 |
|
64 |
### Install the necessary packages
|