Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,29 @@ tags:
|
|
| 8 |
- UNA
|
| 9 |
- SOLAR
|
| 10 |
- MathPILE
|
| 11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
- UNA
|
| 9 |
- SOLAR
|
| 10 |
- MathPILE
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# UNA-POLAR-10.7B-InstructMath-v2
|
| 14 |
+
|
| 15 |
+
## Model description
|
| 16 |
+
|
| 17 |
+
Its a UNA version with DPO over MathPILE Books out of the UNA-SOLAR-10.7B-Instruct-1.0
|
| 18 |
+
|
| 19 |
+
I used MathPILE OUTSTANDING Dataset of great Mathematic material in order to produce this beautiful model :)
|
| 20 |
+
|
| 21 |
+
## Intended uses & limitations
|
| 22 |
+
|
| 23 |
+
If your model has inside UNA technology, cite.
|
| 24 |
+
|
| 25 |
+
## Training and evaluation data
|
| 26 |
+
|
| 27 |
+
UNA-DPO over Attention and MLP's
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.7.1
|
| 33 |
+
- Transformers 4.36.2-UNA
|
| 34 |
+
- Pytorch 2.1.2+cu121
|
| 35 |
+
- Datasets 2.16.0
|
| 36 |
+
- Tokenizers 0.15.
|