Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,15 +1,162 @@
 ---
-library_name: transformers
-license: apache-2.0
-license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
 language:
 - en
-pipeline_tag: text-generation
-base_model: Qwen/Qwen2.5-7B-Instruct
+license: apache-2.0
+library_name: transformers
 tags:
 - chat
 - abliterated
 - uncensored
+base_model: Qwen/Qwen2.5-7B-Instruct
+license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
+pipeline_tag: text-generation
+model-index:
+- name: Qwen2.5-7B-Instruct-abliterated
+  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: 74.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 64.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 52.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 94.12
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 76.22
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 81.54
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 75.94
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 66.96
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      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: 70.74
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=huihui-ai/Qwen2.5-7B-Instruct-abliterated
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # huihui-ai/Qwen2.5-7B-Instruct-abliterated
@@ -109,3 +256,21 @@ The following data has been re-evaluated and calculated as the average for each
 
 The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/eval.sh)
 
+
+# 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/huihui-ai/Qwen2.5-7B-Instruct-abliterated) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**73.04**|
+|ENEM Challenge (No Images)|    74.32|
+|BLUEX (No Images)         |    64.67|
+|OAB Exams                 |    52.85|
+|Assin2 RTE                |    94.12|
+|Assin2 STS                |    76.22|
+|FaQuAD NLI                |    81.54|
+|HateBR Binary             |    75.94|
+|PT Hate Speech Binary     |    66.96|
+|tweetSentBR               |    70.74|
+