Update README.md
Browse files
README.md
CHANGED
|
@@ -223,7 +223,43 @@ This model has been loaded in 4-bit and evaluated with [lighteval](https://githu
|
|
| 223 |
- Tokenizers: 0.22.1
|
| 224 |
|
| 225 |
## Citations
|
| 226 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 227 |
```bibtex
|
| 228 |
@misc{vonwerra2022trl,
|
| 229 |
title = {{TRL: Transformer Reinforcement Learning}},
|
|
|
|
| 223 |
- Tokenizers: 0.22.1
|
| 224 |
|
| 225 |
## Citations
|
| 226 |
+
|
| 227 |
+
```bibtext
|
| 228 |
+
@misc{beck2024xlstmextendedlongshortterm,
|
| 229 |
+
title={xLSTM: Extended Long Short-Term Memory},
|
| 230 |
+
author={Maximilian Beck and Korbinian Pöppel and Markus Spanring and Andreas Auer and Oleksandra Prudnikova and Michael Kopp and Günter Klambauer and Johannes Brandstetter and Sepp Hochreiter},
|
| 231 |
+
year={2024},
|
| 232 |
+
eprint={2405.04517},
|
| 233 |
+
archivePrefix={arXiv},
|
| 234 |
+
primaryClass={cs.LG},
|
| 235 |
+
url={https://arxiv.org/abs/2405.04517},
|
| 236 |
+
}
|
| 237 |
+
```
|
| 238 |
+
|
| 239 |
+
```
|
| 240 |
+
@misc{han2024parameterefficientfinetuninglargemodels,
|
| 241 |
+
title={Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey},
|
| 242 |
+
author={Zeyu Han and Chao Gao and Jinyang Liu and Jeff Zhang and Sai Qian Zhang},
|
| 243 |
+
year={2024},
|
| 244 |
+
eprint={2403.14608},
|
| 245 |
+
archivePrefix={arXiv},
|
| 246 |
+
primaryClass={cs.LG},
|
| 247 |
+
url={https://arxiv.org/abs/2403.14608},
|
| 248 |
+
}
|
| 249 |
+
```
|
| 250 |
+
|
| 251 |
+
```
|
| 252 |
+
@misc{liu2024doraweightdecomposedlowrankadaptation,
|
| 253 |
+
title={DoRA: Weight-Decomposed Low-Rank Adaptation},
|
| 254 |
+
author={Shih-Yang Liu and Chien-Yi Wang and Hongxu Yin and Pavlo Molchanov and Yu-Chiang Frank Wang and Kwang-Ting Cheng and Min-Hung Chen},
|
| 255 |
+
year={2024},
|
| 256 |
+
eprint={2402.09353},
|
| 257 |
+
archivePrefix={arXiv},
|
| 258 |
+
primaryClass={cs.CL},
|
| 259 |
+
url={https://arxiv.org/abs/2402.09353},
|
| 260 |
+
}
|
| 261 |
+
```
|
| 262 |
+
|
| 263 |
```bibtex
|
| 264 |
@misc{vonwerra2022trl,
|
| 265 |
title = {{TRL: Transformer Reinforcement Learning}},
|