Commit
•
b5066cf
1
Parent(s):
e6deb52
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
Llama 2 13b is a pretty decent language model. You know what's probably better? *Two* Llama 2 13b models. In a trenchcoat.
|
| 6 |
+
|
| 7 |
+
Produced by [`bakllama.py`](https://github.com/cg123/mergekit/blob/main/bakllama.py) with this config file:
|
| 8 |
+
```yml
|
| 9 |
+
layer_slices:
|
| 10 |
+
- model: TheBloke/Llama-2-13B-fp16
|
| 11 |
+
start: 0
|
| 12 |
+
end: 40
|
| 13 |
+
- model: TheBloke/Llama-2-13B-fp16
|
| 14 |
+
start: 0
|
| 15 |
+
end: 40
|
| 16 |
+
```
|
| 17 |
+
|
| 18 |
+
No fine tuning was done on this model. Yes, it's still coherent somehow.
|