Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,27 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Qwen/Qwen2.5-7B
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- text-generation-inference
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
## Model Description
|
| 14 |
+
|
| 15 |
+
Optimized Layer Merging (OLM)
|
| 16 |
+
Is a transformer optimization framework implementing automated layer recombination.
|
| 17 |
+
|
| 18 |
+
Olm create Frankenstein's monster out of language models by cherry-picking the best performing layers across different models to create a superior hybrid.
|
| 19 |
+
The core mechanism:
|
| 20 |
+
|
| 21 |
+
- Takes multiple language models as input
|
| 22 |
+
- Uses a base model as the foundation
|
| 23 |
+
- Iteratively replaces individual layers, evaluating performance on specified datasets
|
| 24 |
+
- Keeps the best performing layer at each position based on metrics like perplexity, exact match, and a custom "quality" score
|
| 25 |
+
- Builds a fusion model layer-by-layer while maintaining or improving performance
|
| 26 |
+
|
| 27 |
+
https://github.com/jeffmeloy/olm
|