Update README.md

README.md

@@ -21,10 +21,10 @@ model-index:
       metrics:
         - name: Accuracy (0-shot)
           type: Accuracy (0-shot)
-          value: 67.24
+          value: 65.51
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
     - task:
         type: multiple-choice
       dataset:
@@ -33,10 +33,10 @@ model-index:
       metrics:
         - name: Accuracy (5-shot)
           type: Accuracy (5-shot)
-          value: 51.56
+          value: 53.89
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
     - task:
         type: mix
       dataset:
@@ -45,10 +45,10 @@ model-index:
       metrics:
         - name: Average scores (5-shot)
           type: Average scores (5-shot)
-          value: 54.04
+          value: 53.56
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
     - task:
         type: multiple_choice
       dataset:
@@ -57,10 +57,10 @@ model-index:
       metrics:
         - name: Accuracy (5-shot)
           type: Accuracy (5-shot)
-          value: 45.02
+          value: 44.11
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
     - task:
         type: multiple_choice
       dataset:
@@ -69,10 +69,10 @@ model-index:
       metrics:
         - name: Accuracy (5-shot)
           type: Accuracy (5-shot)
-          value: 29.83
+          value: 32.67
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
     - task:
         type: multiple_choice
       dataset:
@@ -81,10 +81,10 @@ model-index:
       metrics:
         - name: Accuracy (5-shot)
           type: Accuracy (5-shot)
-          value: 56.44
+          value: 56.38
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
     - task:
         type: multiple_choice
       dataset:
@@ -93,10 +93,10 @@ model-index:
       metrics:
         - name: Accuracy (5-shot)
           type: Accuracy (5-shot)
-          value: 43.18
+          value: 43.66
       source:
         name: Paper
-        url: https://paper-url.com
+        url: https://arxiv.org/abs/2403.20266
 ---
 
 # **Model Card for Latxa 13b**
@@ -251,21 +251,18 @@ In order to reproduce our results please follow the instructions in Latxa's [Git
 |
 | XGLM             | 7B   | 57.71  | 23.88    | 41.47   | 22.96   | 24.43   | 26.53     | 24.59    | 32.51 |
 | BLOOM            | 7B   | 57.18  | 27.00    | 40.17   | 25.34   | 28.41   | 27.17     | 25.07    | 33.86 |
-| Mistral          | 7B   | 51.09  | **38.89**| 39.22   | 25.01   | 29.26   | 34.58     | 32.15    | 35.94 |
+| Mistral          | 7B   | 51.09  | **38.89**| 39.22   | 25.01   | **29.26**   | 34.58     | 32.15    | 35.94 |
 | Llama 2          | 7B   | 50.43  | 26.22    | 38.20   | 24.09   | 27.27   | 29.50     | 28.84    | 32.51 |
-| **Latxa v1**     | 7B   | 63.13 | 35.67 | 50.26 | 28.19 | 27.27 | 40.17 | 34.18 | 39.84 |
-| **Latxa v1.1**   | 7B   | **65.72**| 36.89    | **51.78**| **32.44**| **30.40**| **44.37** | **34.20**| **42.26** |
+| **Latxa v1.1**   | 7B   | **65.45**| 37.33    | **52.56**| **30.26**| 25.00| **42.16** | **33.82**| **40.94** |
 |
 | mGPT             | 13B  | 55.39  | 25.00    | 37.56   | 25.00   | 24.15   | 27.17     | 25.73    | 32.14 |
 | Llama 2          | 13B  | 50.63  | 32.00    | 38.98   | 25.90   | 28.98   | 33.53     | 29.66    | 34.36 |
-| **Latxa v1**     | 13B  | 65.85 | **53.56** | **54.49** | 41.19    | **40.06**| 51.14     | 42.92    | **49.95** |
-| **Latxa v1.1**   | 13B  | **67.24**| 51.56  | 54.04     | **45.02**| 29.83    | **56.44** | **43.18**| 49.62 |
+| **Latxa v1.1**   | 13B  | **66.51**| **53.89**  | **53.36**     | **44.11**| **32.67**    | **56.38** | **43.66**| **50.08** |
 |
 | Mixtral          | 8x7B | 52.55  | 50.44    | 45.00   | 26.43   | 37.50   | 42.51     | 39.87    | 41.97 |
 | Yi               | 34B  | 52.22  | 54.56    | 43.90   | 27.30   | 34.66   | 42.57     | 39.68    | 42.05 |
 | Llama 2          | 70B  | 51.62  | 33.56    | 42.55   | 24.16   | 27.84   | 38.43     | 33.08    | 35.47 |
-| **Latxa v1**     | 70B  | 67.57  | **71.78**    | 59.37   | 48.19   | 49.72   | 57.84     | 51.68    | 58.02 |
-| **Latxa v1.1**   | 70B  | **69.76**| 64.89| **61.66**| **60.61**| **53.69**| **61.52** | **54.48**| **60.94** |
+| **Latxa v1.1**   | 70B  | **70.55**| **71.67** | **59.74**| **60.65**| **50.57**| **62.45** | **51.90**| **61.08** |
 
 
 # **Environmental Impact**