Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,7 @@ pipeline_tag: text-generation
|
|
| 16 |
[paper](https://arxiv.org/abs/2410.17215) | [code](https://github.com/thu-coai/MiniPLM)
|
| 17 |
|
| 18 |
**MiniPLM-Mamba-130M** is a 130M model with the [Mamba achitecture](https://github.com/state-spaces/mamba) pre-trained from scratch on [the Pile](https://huggingface.co/datasets/monology/pile-uncopyrighted) using the MiniPLM knowledge distillation framework with the [offcial QWen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) as the teacher model.
|
|
|
|
| 19 |
|
| 20 |
We also open-source the [pre-training corpus](https://huggingface.co/datasets/MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5) refined by Difference Sampling in MiniPLM for reproducibility.
|
| 21 |
|
|
|
|
| 16 |
[paper](https://arxiv.org/abs/2410.17215) | [code](https://github.com/thu-coai/MiniPLM)
|
| 17 |
|
| 18 |
**MiniPLM-Mamba-130M** is a 130M model with the [Mamba achitecture](https://github.com/state-spaces/mamba) pre-trained from scratch on [the Pile](https://huggingface.co/datasets/monology/pile-uncopyrighted) using the MiniPLM knowledge distillation framework with the [offcial QWen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) as the teacher model.
|
| 19 |
+
This model shows the flexibility of the MiniPLM framework in conducting knowledge distillation across model families.
|
| 20 |
|
| 21 |
We also open-source the [pre-training corpus](https://huggingface.co/datasets/MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5) refined by Difference Sampling in MiniPLM for reproducibility.
|
| 22 |
|