Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,9 @@ Data quality is another critical factor. Large language models require high-qual
|
|
| 39 |
- **Dataset**: OpenO1-SFT (complete dataset)
|
| 40 |
- **Training Duration**: 1 epoch
|
| 41 |
|
|
|
|
|
|
|
|
|
|
| 42 |
## Model Specifications
|
| 43 |
|
| 44 |
- **Architecture**: Transformer decoder (135M parameters)
|
|
@@ -57,6 +60,8 @@ Data quality is another critical factor. Large language models require high-qual
|
|
| 57 |
|
| 58 |
- No RoPE scaling applied
|
| 59 |
- No quantization used
|
|
|
|
|
|
|
| 60 |
|
| 61 |
## Usage
|
| 62 |
|
|
|
|
| 39 |
- **Dataset**: OpenO1-SFT (complete dataset)
|
| 40 |
- **Training Duration**: 1 epoch
|
| 41 |
|
| 42 |
+
<details>
|
| 43 |
+
<summary>More details</summary>
|
| 44 |
+
|
| 45 |
## Model Specifications
|
| 46 |
|
| 47 |
- **Architecture**: Transformer decoder (135M parameters)
|
|
|
|
| 60 |
|
| 61 |
- No RoPE scaling applied
|
| 62 |
- No quantization used
|
| 63 |
+
|
| 64 |
+
</details>
|
| 65 |
|
| 66 |
## Usage
|
| 67 |
|