Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model:
|
| 3 |
-
- meta-llama/Meta-Llama-3-8B
|
| 4 |
-
library_name: transformers
|
| 5 |
-
tags:
|
| 6 |
-
- mergekit
|
| 7 |
-
- merge
|
| 8 |
-
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
# model
|
| 11 |
|
| 12 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
@@ -37,4 +51,4 @@ slices:
|
|
| 37 |
merge_method: passthrough
|
| 38 |
dtype: bfloat16
|
| 39 |
|
| 40 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- meta-llama/Meta-Llama-3-8B
|
| 4 |
+
library_name: transformers
|
| 5 |
+
tags:
|
| 6 |
+
- mergekit
|
| 7 |
+
- merge
|
| 8 |
+
- llama3
|
| 9 |
+
license: llama3
|
| 10 |
+
language:
|
| 11 |
+
- en
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
Meta's Llama 3 8B pruned to 7B parameters(w/ 28 layers). Layers to prune selected using PruneMe repo on Github.
|
| 15 |
+
|
| 16 |
+
- layers_to_skip = 4
|
| 17 |
+
- Layer 23 to 27 has the minimum average distance of 0.18376044921875
|
| 18 |
+
|
| 19 |
+
- [ ] To Do : Post pruning training.
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
# model
|
| 25 |
|
| 26 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
| 51 |
merge_method: passthrough
|
| 52 |
dtype: bfloat16
|
| 53 |
|
| 54 |
+
```
|