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](1) on the ModelCard YAML metadata.

README.md

@@ -80,6 +80,19 @@ model-index:
     - type: f1_macro
       value: 68.1
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/Phi-Bode
+      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: 30.57
       name: pearson
@@ -107,7 +120,7 @@ model-index:
       name: Text Generation
     dataset:
       name: HateBR Binary
-      type: eduagarcia/portuguese_benchmark
+      type: ruanchaves/hatebr
       split: test
       args:
         num_few_shot: 25
@@ -115,6 +128,19 @@ model-index:
     - type: f1_macro
       value: 60.51
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/Phi-Bode
+      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: 54.6
       name: f1-macro