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](6) on the ModelCard YAML metadata.

README.md

@@ -8,9 +8,9 @@ tags:
 - analytics
 - analise-dados
 - portugues-BR
-base_model: codellama/CodeLlama-7b-Instruct-hf
 datasets:
 - semantixai/Test-Dataset-Lloro
+base_model: codellama/CodeLlama-7b-Instruct-hf
 model-index:
 - name: LloroV2
   results:
@@ -75,6 +75,19 @@ model-index:
     - type: f1_macro
       value: 57.19
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=semantixai/LloroV2
+      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: 26.81
       name: pearson
@@ -102,7 +115,7 @@ model-index:
       name: Text Generation
     dataset:
       name: HateBR Binary
-      type: eduagarcia/portuguese_benchmark
+      type: ruanchaves/hatebr
       split: test
       args:
         num_few_shot: 25
@@ -110,6 +123,19 @@ model-index:
     - type: f1_macro
       value: 68.02
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=semantixai/LloroV2
+      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: 38.53
       name: f1-macro