Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,14 @@ library_name: transformers
|
|
| 22 |
|
| 23 |
## GGUF Conversion
|
| 24 |
|
| 25 |
-
This is a llama.cpp conversion in F16, Q8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
## Introduction
|
| 28 |
We introduce AceMath, a family of frontier models designed for mathematical reasoning. The models in AceMath family, including AceMath-1.5B/7B/72B-Instruct and AceMath-7B/72B-RM, are <b>Improved using Qwen</b>.
|
|
|
|
| 22 |
|
| 23 |
## GGUF Conversion
|
| 24 |
|
| 25 |
+
This is a llama.cpp conversion in F16, Q8 for the original https://huggingface.co/nvidia/AceMath-72B-Instruct model published by Nvidia.
|
| 26 |
+
In order to meet the file size upload limit the GGUF file was split into two parts.
|
| 27 |
+
|
| 28 |
+
It can be recombined by running:
|
| 29 |
+
```bash
|
| 30 |
+
./recombine.sh
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
|
| 34 |
## Introduction
|
| 35 |
We introduce AceMath, a family of frontier models designed for mathematical reasoning. The models in AceMath family, including AceMath-1.5B/7B/72B-Instruct and AceMath-7B/72B-RM, are <b>Improved using Qwen</b>.
|