Pretergeek commited on
Commit
4cdf90d
·
verified ·
1 Parent(s): c94c33e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -14
README.md CHANGED
@@ -116,20 +116,6 @@ The model was fine-tuned using [Rank-Stabilized LoRA](https://huggingface.co/blo
116
 
117
  After fine-tuning, the model was tested using passkey retrieval and achieved a score of 100%.
118
 
119
- ## Citations
120
- ```
121
- @misc{zhu2024poseefficientcontextwindow,
122
- title={PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training},
123
- author={Dawei Zhu and Nan Yang and Liang Wang and Yifan Song and Wenhao Wu and Furu Wei and Sujian Li},
124
- year={2024},
125
- eprint={2309.10400},
126
- archivePrefix={arXiv},
127
- primaryClass={cs.CL},
128
- url={https://arxiv.org/abs/2309.10400},
129
- }
130
- ```
131
-
132
-
133
  # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
134
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Pretergeek__OpenChat-3.5-0106_32K-PoSE)
135
 
@@ -143,3 +129,15 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
143
  |MuSR (0-shot) |11.33|
144
  |MMLU-PRO (5-shot) |11.46|
145
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
 
117
  After fine-tuning, the model was tested using passkey retrieval and achieved a score of 100%.
118
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
120
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Pretergeek__OpenChat-3.5-0106_32K-PoSE)
121
 
 
129
  |MuSR (0-shot) |11.33|
130
  |MMLU-PRO (5-shot) |11.46|
131
 
132
+ # Citation
133
+ ```
134
+ @misc{zhu2024poseefficientcontextwindow,
135
+ title={PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training},
136
+ author={Dawei Zhu and Nan Yang and Liang Wang and Yifan Song and Wenhao Wu and Furu Wei and Sujian Li},
137
+ year={2024},
138
+ eprint={2309.10400},
139
+ archivePrefix={arXiv},
140
+ primaryClass={cs.CL},
141
+ url={https://arxiv.org/abs/2309.10400},
142
+ }
143
+ ```