Hugging Face's logo

OpenLLM-Ro
/
RoLlama2-7b-Base-2024-05-14

Text Generation
Transformers
PyTorch
Romanian
llama
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
mihaimasala commited on
Commit
e691ba4
•
1 Parent(s): a64c91f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +71 -0
README.md CHANGED
@@ -584,6 +584,77 @@ print(tokenizer.decode(outputs[0]))
584
  </tbody>
585
  </table>
586
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
587
  ## RoLlama2 Model Family
588
 
589
  | Model | Link |
 
584
  </tbody>
585
  </table>
586
 
587
+
588
+ <table>
589
+ <tbody>
590
+ <tr>
591
+ <td></td>
592
+ <td colspan="4"><center><strong>LaRoSeDa</strong></center></td>
593
+ <td colspan="4"><center><strong>WMT</strong></center></td>
594
+ </tr>
595
+ <tr>
596
+ <td></td>
597
+ <td colspan="2"><center><strong>Few-shot</strong></center></td>
598
+ <td colspan="2"><center><strong>Finetuned</strong></center></td>
599
+ <td colspan="2"><center><strong>Few-shot</strong></center></td>
600
+ <td colspan="2"><center><strong>Finetuned</strong></center></td>
601
+ </tr>
602
+ <tr>
603
+ <td></td>
604
+ <td><center><strong>Binary<br>(Macro F1)</strong></center></td>
605
+ <td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
606
+ <td><center><strong>Binary<br>(Macro F1)</strong></center></td>
607
+ <td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
608
+ <td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
609
+ <td><center><strong>RO-EN<br>(Bleu)</strong></center></td>
610
+ <td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
611
+ <td><center><strong>RO-EN<br>(Bleu)</strong></center>
612
+ </tr>
613
+ <tr>
614
+ <td>Llama-2-7b-hf</td><td><center><strong>93.19</strong></center></td><td><center>54.11</center></td><td><center>98.43</center></td><td><center>87.22</center></td><td><center><strong>14.90</strong></center></td><td><center><strong>26.61</strong></center></td><td><center>24.95</center></td><td><center>39.09</center></td>
615
+ </tr>
616
+ <tr>
617
+ <td><em>RoLlama2-7b-Base</em></td><td><center><em>83.25</em></center></td><td><center><em><strong>61.04</strong></em></center></td><td><center><em><strong>98.97</strong></em></center></td><td><center><em><strong>87.72</strong></em></center></td><td><center><em>10.01</em></center></td><td><center><em>13.03</em></center></td><td><center><em><strong>27.85</strong></em></center></td><td><center><em><strong>39.30</strong></em></center></td>
618
+ </tr>
619
+ </tbody>
620
+ </table>
621
+
622
+
623
+ <table>
624
+ <tbody>
625
+ <tr>
626
+ <td></td>
627
+ <td colspan="4"></td><center><strong>XQuAD</strong></center></td>
628
+ <td colspan="4"><center><strong>STS</strong></center></td>
629
+ </tr>
630
+ <tr>
631
+ <td></td>
632
+ <td colspan="2"><center><strong>Few-shot</strong></center></td>
633
+ <td colspan="2"><center><strong>Finetuned</strong></center></td>
634
+ <td colspan="2"><center><strong>Few-shot</strong></center></td>
635
+ <td colspan="2"><center><strong>Finetuned</strong></center></td>
636
+ </tr>
637
+ <tr>
638
+ <td></td>
639
+ </td>
640
+ <td><center><strong>-<br>(EM)</strong></center></td>
641
+ <td><center><strong>-<br>(F1)</strong></center></td>
642
+ <td><center><strong>-<br>(EM)</strong></center></td>
643
+ <td><center><strong>-<br>(F1)</strong></center></td>
644
+ <td><center><strong>-<br>(Spearman)</strong></center></td>
645
+ <td><center><strong>-<br>(Pearson)</strong></center></td>
646
+ <td><center><strong>-<br>(Spearman)</strong></center></td>
647
+ <td><center><strong>-<br>(Pearson)</strong></center></td>
648
+ </tr>
649
+ <tr>
650
+ <td>Llama-2-7b-hf</td><td><center><strong>38.91</strong></center></td><td><center><strong>56.82</strong></center></td><td><center>65.46</center></td><td><center>79.42</center></td><td><center><strong>9.08</strong></center></td><td><center><strong>9.07</strong></center></td><td><center><strong>79.93</strong></center></td><td><center><strong>81.08</strong></center></td>
651
+ </tr>
652
+ <tr>
653
+ <td><em>RoLlama2-7b-Base</em></td><td><center><em>30.15</em></center></td><td><center><em>47.03</em></center></td><td><center><em><strong>67.06</strong></em></center></td><td><center><em><strong>79.96</strong></em></center></td><td><center><em>7.89</em></center></td><td><center><em>7.98</em></center></td><td><center><em>71.75</em></center></td><td><center><em>71.99</em></center></td>
654
+ </tr>
655
+ </tbody>
656
+ </table>
657
+
658
  ## RoLlama2 Model Family
659
 
660
  | Model | Link |