Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,9 +1,9 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-Nemo-Base-2407
 tags:
 - generated_from_trainer
 - axolotl
+base_model: mistralai/Mistral-Nemo-Base-2407
 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-2.9.3-mistral-nemo-12b
+  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: 72.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 62.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 52.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 93.08
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 80.83
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 81.28
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 85.85
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 73.07
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      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: 72.36
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # Dolphin 2.9.3 Mistral Nemo 12b 🐬
@@ -483,3 +630,22 @@ The following hyperparameters were used during training:
 - Pytorch 2.2.2+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1
+
+
+# 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-2.9.3-mistral-nemo-12b) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**74.86**|
+|ENEM Challenge (No Images)|    72.08|
+|BLUEX (No Images)         |    62.45|
+|OAB Exams                 |    52.71|
+|Assin2 RTE                |    93.08|
+|Assin2 STS                |    80.83|
+|FaQuAD NLI                |    81.28|
+|HateBR Binary             |    85.85|
+|PT Hate Speech Binary     |    73.07|
+|tweetSentBR               |    72.36|
+