Update README.md
Browse files
README.md
CHANGED
|
@@ -187,6 +187,8 @@ The dataset integrates three primary components:
|
|
| 187 |
* [PyTorch](https://github.com/pytorch/pytorch)
|
| 188 |
* [Transformers](https://github.com/huggingface/transformers)
|
| 189 |
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
|
|
|
|
|
|
|
| 190 |
|
| 191 |
## Hardware
|
| 192 |
Note that by default, the Phi-4-mini-flash-reasoning model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:
|
|
|
|
| 187 |
* [PyTorch](https://github.com/pytorch/pytorch)
|
| 188 |
* [Transformers](https://github.com/huggingface/transformers)
|
| 189 |
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
|
| 190 |
+
* [Mamba](https://github.com/state-spaces/mamba)
|
| 191 |
+
* [Causal-Conv1d](https://github.com/Dao-AILab/causal-conv1d)
|
| 192 |
|
| 193 |
## Hardware
|
| 194 |
Note that by default, the Phi-4-mini-flash-reasoning model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:
|