Update README.md
Browse files
README.md
CHANGED
|
@@ -31,8 +31,8 @@ This is our third generation model featuring the new Mamba2 architecture with at
|
|
| 31 |
If you're interested in more technical details that covers the training process, architecture, and performance: <a href="https://outeai.com/blog/lite-oute-2-mamba2attn" target="_blank">Read the full blog post here</a>
|
| 32 |
|
| 33 |
## Model Variants
|
| 34 |
-
- [Lite-Oute-2-Mamba2Attn-Instruct](https://huggingface.co/OuteAI/Lite-Oute-2-Mamba2Attn-Instruct)
|
| 35 |
-
- [Lite-Oute-2-Mamba2Attn-Base](https://huggingface.co/OuteAI/Lite-Oute-2-Mamba2Attn-Base)
|
| 36 |
|
| 37 |
## Training Details
|
| 38 |
The model was pre-trained on 30 billion tokens using a balanced mixture of datasets:
|
|
|
|
| 31 |
If you're interested in more technical details that covers the training process, architecture, and performance: <a href="https://outeai.com/blog/lite-oute-2-mamba2attn" target="_blank">Read the full blog post here</a>
|
| 32 |
|
| 33 |
## Model Variants
|
| 34 |
+
- [Lite-Oute-2-Mamba2Attn-250M-Instruct](https://huggingface.co/OuteAI/Lite-Oute-2-Mamba2Attn-250M-Instruct)
|
| 35 |
+
- [Lite-Oute-2-Mamba2Attn-250M-Base](https://huggingface.co/OuteAI/Lite-Oute-2-Mamba2Attn-250M-Base)
|
| 36 |
|
| 37 |
## Training Details
|
| 38 |
The model was pre-trained on 30 billion tokens using a balanced mixture of datasets:
|