Liu Hong Yuan Tom
commited on
Commit
•
76728cd
1
Parent(s):
db15e4b
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ datasets:
|
|
| 14 |
- microsoft/orca-math-word-problems-200k
|
| 15 |
---
|
| 16 |
|
|
|
|
|
|
|
| 17 |
# Uploaded model
|
| 18 |
|
| 19 |
- **Developed by:** NotAiLOL
|
|
@@ -26,6 +28,11 @@ This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unsloth
|
|
| 26 |
|
| 27 |
# Details
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
The model follows the Alpaca format:
|
| 30 |
```
|
| 31 |
<|im_start|>system
|
|
@@ -37,7 +44,3 @@ You are a professional mathematician.|im_end|>
|
|
| 37 |
<|im_start|>assistant
|
| 38 |
{}
|
| 39 |
```
|
| 40 |
-
|
| 41 |
-
**Training Loss Graph**
|
| 42 |
-
|
| 43 |
-
_29 PM.png…]()
|
|
|
|
| 14 |
- microsoft/orca-math-word-problems-200k
|
| 15 |
---
|
| 16 |
|
| 17 |
+
**Coding model comming soon!**
|
| 18 |
+
|
| 19 |
# Uploaded model
|
| 20 |
|
| 21 |
- **Developed by:** NotAiLOL
|
|
|
|
| 28 |
|
| 29 |
# Details
|
| 30 |
|
| 31 |
+
This model was trained on [microsoft/orca-math-word-problems-200k](https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k) for 3 epochs with **rsLoRA** + **QLoRA**.
|
| 32 |
+
|
| 33 |
+
**Training Loss Graph**
|
| 34 |
+
|
| 35 |
+
|
| 36 |
The model follows the Alpaca format:
|
| 37 |
```
|
| 38 |
<|im_start|>system
|
|
|
|
| 44 |
<|im_start|>assistant
|
| 45 |
{}
|
| 46 |
```
|
|
|
|
|
|
|
|
|
|
|
|