Update README.md
Browse files
README.md
CHANGED
|
@@ -4,11 +4,19 @@ tags:
|
|
| 4 |
- merge
|
| 5 |
- mergekit
|
| 6 |
- lazymergekit
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# Mnemosyne-7B
|
| 10 |
|
| 11 |
-
Mnemosyne-7B is
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
## 🧩 Configuration
|
| 14 |
|
|
@@ -21,4 +29,6 @@ merge_method: model_stock
|
|
| 21 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 22 |
dtype: bfloat16
|
| 23 |
|
| 24 |
-
```
|
|
|
|
|
|
|
|
|
| 4 |
- merge
|
| 5 |
- mergekit
|
| 6 |
- lazymergekit
|
| 7 |
+
metrics:
|
| 8 |
+
- code_eval
|
| 9 |
+
- accuracy
|
| 10 |
---
|
| 11 |
|
| 12 |
# Mnemosyne-7B
|
| 13 |
|
| 14 |
+
Mnemosyne-7B is an experimental large language model (LLM) created by merging several pre-trained models designed for informative and educational purposes. It combines the strengths of these models with the hope of achieving a highly informative and comprehensive LLM.
|
| 15 |
+
|
| 16 |
+
### Important Note:
|
| 17 |
+
|
| 18 |
+
This is an experimental model, and its performance and capabilities are not guaranteed. Further testing and evaluation are required to assess its effectiveness.
|
| 19 |
+
|
| 20 |
|
| 21 |
## 🧩 Configuration
|
| 22 |
|
|
|
|
| 29 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 30 |
dtype: bfloat16
|
| 31 |
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
Mnemosyne-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|