Fixing some errors of the leaderboard evaluation results in the ModelCard yaml

The name of a few benchmarks are incorrect on the model metadata.

This commit fixes some minor errors of the [last PR](2) on the ModelCard YAML metadata.

README.md

@@ -68,6 +68,19 @@ model-index:
     - type: f1_macro
       value: 90.31
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 STS
+      type: eduagarcia/portuguese_benchmark
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
     - type: pearson
       value: 76.55
       name: pearson
@@ -95,7 +108,7 @@ model-index:
       name: Text Generation
     dataset:
       name: HateBR Binary
-      type: eduagarcia/portuguese_benchmark
+      type: ruanchaves/hatebr
       split: test
       args:
         num_few_shot: 25
@@ -103,6 +116,19 @@ model-index:
     - type: f1_macro
       value: 79.21
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cnmoro/Mistral-7B-Portuguese
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: PT Hate Speech Binary
+      type: hate_speech_portuguese
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
     - type: f1_macro
       value: 68.87
       name: f1-macro