|
--- |
|
license: apache-2.0 |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- liminerity/merge2 |
|
- liminerity/merge1 |
|
--- |
|
Made by Liminerity <# |
|
# INEX4-7b |
|
|
|
INEX4-7b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): |
|
* [liminerity/merge2](https://huggingface.co/liminerity/merge2) |
|
* [liminerity/merge1](https://huggingface.co/liminerity/merge1) |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
slices: |
|
- sources: |
|
- model: liminerity/Ingot-7b-slerp-7-forged |
|
layer_range: [0, 32] |
|
- model: yam-peleg/Experiment26-7B |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: liminerity/Ingot-7b-slerp-7-forged |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
model: liminerity/merge |
|
|
|
slices: |
|
- sources: |
|
- model: liminerity/Ingot-7b-slerp-7-forged |
|
layer_range: [0, 32] |
|
- model: liminerity/merge |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: liminerity/Ingot-7b-slerp-7-forged |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
model: liminerity/merge1 |
|
|
|
slices: |
|
- sources: |
|
- model: yam-peleg/Experiment26-7B |
|
layer_range: [0, 32] |
|
- model: liminerity/merge1 |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: yam-peleg/Experiment26-7B |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: float16 |
|
model: liminerity/merge2 |
|
|
|
slices: |
|
- sources: |
|
- model: liminerity/merge2 |
|
layer_range: [0, 32] |
|
- model: liminerity/merge1 |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: liminerity/merge2 |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
model: INEX-7b |
|
``` |