Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,48 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: []
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- mergekit
|
| 6 |
+
- merge
|
| 7 |
+
|
| 8 |
---
|
| 9 |
+
# Fett-uccine-Long-Noodle-7B-120k-Context
|
| 10 |
+
|
| 11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 12 |
+
|
| 13 |
+
## Merge Details
|
| 14 |
+
A merge with Fett-uccine and Mistral Yarn 120k ctx.
|
| 15 |
+
|
| 16 |
+
Credit to Nitral for the merge script and idea.
|
| 17 |
+
### Merge Method
|
| 18 |
+
|
| 19 |
+
This model was merged using the SLERP merge method.
|
| 20 |
+
|
| 21 |
+
### Models Merged
|
| 22 |
+
|
| 23 |
+
The following models were included in the merge:
|
| 24 |
+
* Z:\ModelColdStorage\Yarn-Mistral-7b-128k
|
| 25 |
+
* Z:\ModelColdStorage\Fett-uccine-7B
|
| 26 |
+
|
| 27 |
+
### Configuration
|
| 28 |
+
|
| 29 |
+
The following YAML configuration was used to produce this model:
|
| 30 |
+
|
| 31 |
+
```yaml
|
| 32 |
+
slices:
|
| 33 |
+
- sources:
|
| 34 |
+
- model: Z:\ModelColdStorage\Fett-uccine-7B
|
| 35 |
+
layer_range: [0, 32]
|
| 36 |
+
- model: Z:\ModelColdStorage\Yarn-Mistral-7b-128k
|
| 37 |
+
layer_range: [0, 32]
|
| 38 |
+
merge_method: slerp
|
| 39 |
+
base_model: Z:\ModelColdStorage\Fett-uccine-7B
|
| 40 |
+
parameters:
|
| 41 |
+
t:
|
| 42 |
+
- filter: self_attn
|
| 43 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
| 44 |
+
- filter: mlp
|
| 45 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
| 46 |
+
- value: 0.5
|
| 47 |
+
dtype: bfloat16
|
| 48 |
+
```
|