Nitral
		
	commited on
		
		
					Update README.md
Browse files
    	
        README.md
    CHANGED
    
    | 
         @@ -18,7 +18,8 @@ This is a merge of pre-trained language models created using [mergekit](https:// 
     | 
|
| 18 | 
         
             
            This model was merged using the SLERP merge method.
         
     | 
| 19 | 
         | 
| 20 | 
         | 
| 21 | 
         
            -
             
     | 
| 
         | 
|
| 22 | 
         | 
| 23 | 
         
             
            
         
     | 
| 24 | 
         | 
| 
         @@ -49,4 +50,97 @@ parameters: 
     | 
|
| 49 | 
         
             
                  value: [1, 0.5, 0.7, 0.3, 0]
         
     | 
| 50 | 
         
             
                - value: 0.5
         
     | 
| 51 | 
         
             
            dtype: bfloat16
         
     | 
| 52 | 
         
            -
            ```
         
     | 
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 18 | 
         
             
            This model was merged using the SLERP merge method.
         
     | 
| 19 | 
         | 
| 20 | 
         | 
| 21 | 
         
            +
             
     | 
| 22 | 
         
            +
            
         
     | 
| 23 | 
         | 
| 24 | 
         
             
            
         
     | 
| 25 | 
         | 
| 
         | 
|
| 50 | 
         
             
                  value: [1, 0.5, 0.7, 0.3, 0]
         
     | 
| 51 | 
         
             
                - value: 0.5
         
     | 
| 52 | 
         
             
            dtype: bfloat16
         
     | 
| 53 | 
         
            +
            ```
         
     | 
| 54 | 
         
            +
             
     | 
| 55 | 
         
            +
            @misc{open-llm-leaderboard,
         
     | 
| 56 | 
         
            +
              author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
         
     | 
| 57 | 
         
            +
              title = {Open LLM Leaderboard},
         
     | 
| 58 | 
         
            +
              year = {2023},
         
     | 
| 59 | 
         
            +
              publisher = {Hugging Face},
         
     | 
| 60 | 
         
            +
              howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
         
     | 
| 61 | 
         
            +
            }
         
     | 
| 62 | 
         
            +
            @software{eval-harness,
         
     | 
| 63 | 
         
            +
              author       = {Gao, Leo and
         
     | 
| 64 | 
         
            +
                              Tow, Jonathan and
         
     | 
| 65 | 
         
            +
                              Biderman, Stella and
         
     | 
| 66 | 
         
            +
                              Black, Sid and
         
     | 
| 67 | 
         
            +
                              DiPofi, Anthony and
         
     | 
| 68 | 
         
            +
                              Foster, Charles and
         
     | 
| 69 | 
         
            +
                              Golding, Laurence and
         
     | 
| 70 | 
         
            +
                              Hsu, Jeffrey and
         
     | 
| 71 | 
         
            +
                              McDonell, Kyle and
         
     | 
| 72 | 
         
            +
                              Muennighoff, Niklas and
         
     | 
| 73 | 
         
            +
                              Phang, Jason and
         
     | 
| 74 | 
         
            +
                              Reynolds, Laria and
         
     | 
| 75 | 
         
            +
                              Tang, Eric and
         
     | 
| 76 | 
         
            +
                              Thite, Anish and
         
     | 
| 77 | 
         
            +
                              Wang, Ben and
         
     | 
| 78 | 
         
            +
                              Wang, Kevin and
         
     | 
| 79 | 
         
            +
                              Zou, Andy},
         
     | 
| 80 | 
         
            +
              title        = {A framework for few-shot language model evaluation},
         
     | 
| 81 | 
         
            +
              month        = sep,
         
     | 
| 82 | 
         
            +
              year         = 2021,
         
     | 
| 83 | 
         
            +
              publisher    = {Zenodo},
         
     | 
| 84 | 
         
            +
              version      = {v0.0.1},
         
     | 
| 85 | 
         
            +
              doi          = {10.5281/zenodo.5371628},
         
     | 
| 86 | 
         
            +
              url          = {https://doi.org/10.5281/zenodo.5371628}
         
     | 
| 87 | 
         
            +
            }
         
     | 
| 88 | 
         
            +
            @misc{clark2018think,
         
     | 
| 89 | 
         
            +
                  title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
         
     | 
| 90 | 
         
            +
                  author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
         
     | 
| 91 | 
         
            +
                  year={2018},
         
     | 
| 92 | 
         
            +
                  eprint={1803.05457},
         
     | 
| 93 | 
         
            +
                  archivePrefix={arXiv},
         
     | 
| 94 | 
         
            +
                  primaryClass={cs.AI}
         
     | 
| 95 | 
         
            +
            }
         
     | 
| 96 | 
         
            +
            @misc{zellers2019hellaswag,
         
     | 
| 97 | 
         
            +
                  title={HellaSwag: Can a Machine Really Finish Your Sentence?},
         
     | 
| 98 | 
         
            +
                  author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
         
     | 
| 99 | 
         
            +
                  year={2019},
         
     | 
| 100 | 
         
            +
                  eprint={1905.07830},
         
     | 
| 101 | 
         
            +
                  archivePrefix={arXiv},
         
     | 
| 102 | 
         
            +
                  primaryClass={cs.CL}
         
     | 
| 103 | 
         
            +
            }
         
     | 
| 104 | 
         
            +
            @misc{hendrycks2021measuring,
         
     | 
| 105 | 
         
            +
                  title={Measuring Massive Multitask Language Understanding},
         
     | 
| 106 | 
         
            +
                  author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
         
     | 
| 107 | 
         
            +
                  year={2021},
         
     | 
| 108 | 
         
            +
                  eprint={2009.03300},
         
     | 
| 109 | 
         
            +
                  archivePrefix={arXiv},
         
     | 
| 110 | 
         
            +
                  primaryClass={cs.CY}
         
     | 
| 111 | 
         
            +
            }
         
     | 
| 112 | 
         
            +
            @misc{lin2022truthfulqa,
         
     | 
| 113 | 
         
            +
                  title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
         
     | 
| 114 | 
         
            +
                  author={Stephanie Lin and Jacob Hilton and Owain Evans},
         
     | 
| 115 | 
         
            +
                  year={2022},
         
     | 
| 116 | 
         
            +
                  eprint={2109.07958},
         
     | 
| 117 | 
         
            +
                  archivePrefix={arXiv},
         
     | 
| 118 | 
         
            +
                  primaryClass={cs.CL}
         
     | 
| 119 | 
         
            +
            }
         
     | 
| 120 | 
         
            +
            @misc{DBLP:journals/corr/abs-1907-10641,
         
     | 
| 121 | 
         
            +
                  title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
         
     | 
| 122 | 
         
            +
                  author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
         
     | 
| 123 | 
         
            +
                  year={2019},
         
     | 
| 124 | 
         
            +
                  eprint={1907.10641},
         
     | 
| 125 | 
         
            +
                  archivePrefix={arXiv},
         
     | 
| 126 | 
         
            +
                  primaryClass={cs.CL}
         
     | 
| 127 | 
         
            +
            }
         
     | 
| 128 | 
         
            +
            @misc{DBLP:journals/corr/abs-2110-14168,
         
     | 
| 129 | 
         
            +
                  title={Training Verifiers to Solve Math Word Problems},
         
     | 
| 130 | 
         
            +
                  author={Karl Cobbe and
         
     | 
| 131 | 
         
            +
                              Vineet Kosaraju and
         
     | 
| 132 | 
         
            +
                              Mohammad Bavarian and
         
     | 
| 133 | 
         
            +
                              Mark Chen and
         
     | 
| 134 | 
         
            +
                              Heewoo Jun and
         
     | 
| 135 | 
         
            +
                              Lukasz Kaiser and
         
     | 
| 136 | 
         
            +
                              Matthias Plappert and
         
     | 
| 137 | 
         
            +
                              Jerry Tworek and
         
     | 
| 138 | 
         
            +
                              Jacob Hilton and
         
     | 
| 139 | 
         
            +
                              Reiichiro Nakano and
         
     | 
| 140 | 
         
            +
                              Christopher Hesse and
         
     | 
| 141 | 
         
            +
                              John Schulman},
         
     | 
| 142 | 
         
            +
                  year={2021},
         
     | 
| 143 | 
         
            +
                  eprint={2110.14168},
         
     | 
| 144 | 
         
            +
                  archivePrefix={arXiv},
         
     | 
| 145 | 
         
            +
                  primaryClass={cs.CL}
         
     | 
| 146 | 
         
            +
            }
         
     |