Adding the Open Portuguese LLM Leaderboard Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/eduagarcia-temp/portuguese-leaderboard-results-to-modelcard

The purpose of this PR is to add evaluation results from the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard) to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/eduagarcia-temp/portuguese-leaderboard-results-to-modelcard/discussions

README.md

@@ -1,9 +1,9 @@
 ---
 license: apache-2.0
-base_model: 01-ai/Yi-1.5-34B
 tags:
 - generated_from_trainer
 - axolotl
+base_model: 01-ai/Yi-1.5-34B
 datasets:
 - cognitivecomputations/Dolphin-2.9
 - teknium/OpenHermes-2.5
@@ -13,6 +13,153 @@ datasets:
 - microsoft/orca-math-word-problems-200k
 - Locutusque/function-calling-chatml
 - internlm/Agent-FLAN
+model-index:
+- name: dolphin-2.9.1-yi-1.5-34b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: ENEM Challenge (No Images)
+      type: eduagarcia/enem_challenge
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 69.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BLUEX (No Images)
+      type: eduagarcia-temp/BLUEX_without_images
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 63.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: OAB Exams
+      type: eduagarcia/oab_exams
+      split: train
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc
+      value: 51.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 RTE
+      type: assin2
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: f1_macro
+      value: 91.17
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      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: 82.52
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: FaQuAD NLI
+      type: ruanchaves/faquad-nli
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
+    - type: f1_macro
+      value: 79.81
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HateBR Binary
+      type: ruanchaves/hatebr
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 84.68
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      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: 70.81
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: tweetSentBR
+      type: eduagarcia/tweetsentbr_fewshot
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 68.01
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # Dolphin 2.9.1 Yi 1.5 34b 🐬
@@ -246,4 +393,23 @@ The following hyperparameters were used during training:
 - Transformers 4.40.0.dev0
 - Pytorch 2.2.2+cu121
 - Datasets 2.15.0
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0
+
+
+# Open Portuguese LLM Leaderboard Evaluation Results  
+
+Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/cognitivecomputations/dolphin-2.9.1-yi-1.5-34b) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**73.48**|
+|ENEM Challenge (No Images)|    69.35|
+|BLUEX (No Images)         |    63.56|
+|OAB Exams                 |    51.44|
+|Assin2 RTE                |    91.17|
+|Assin2 STS                |    82.52|
+|FaQuAD NLI                |    79.81|
+|HateBR Binary             |    84.68|
+|PT Hate Speech Binary     |    70.81|
+|tweetSentBR               |    68.01|
+