Ashiwn Shirke commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- nlp
|
| 7 |
+
- language-model
|
| 8 |
+
- mamba
|
| 9 |
+
- openslm
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# OpenSLM Mamba 30M
|
| 13 |
+
|
| 14 |
+
This is the Mamba model trained with approximately 30M parameters, as part of the [OpenSLM](https://github.com/Ashwin3919/OpenSLM) project.
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
- **Architecture:** Mamba
|
| 19 |
+
- **Parameters:** ~30M
|
| 20 |
+
- **License:** Apache 2.0
|
| 21 |
+
- **Language:** English
|
| 22 |
+
|
| 23 |
+
## Performance
|
| 24 |
+
|
| 25 |
+
Based on the evaluation metrics, the model achieved the following performance:
|
| 26 |
+
|
| 27 |
+
- **Best Validation Loss:** `2.5662`
|
| 28 |
+
|
| 29 |
+
## Usage
|
| 30 |
+
|
| 31 |
+
For detailed usage instructions, please refer to the [OpenSLM repository](https://github.com/Ashwin3919/OpenSLM).
|