Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -3,10 +3,157 @@ license: other
 license_name: yi-license
 license_link: LICENSE
 widget:
-  - text: "你好! 你叫什么名字!"
-    output:
-      text: "你好，我的名字叫聚言，很高兴见到你。"
+- text: 你好! 你叫什么名字!
+  output:
+    text: 你好，我的名字叫聚言，很高兴见到你。
 pipeline_tag: text-generation
+model-index:
+- name: OrionStar-Yi-34B-Chat
+  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: 70.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 62.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 50.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 91.71
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 79.69
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 78.4
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 84.44
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 65.91
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      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: 72.62
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=OrionStarAI/OrionStar-Yi-34B-Chat
+      name: Open Portuguese LLM Leaderboard
 ---
 
 <!-- markdownlint-disable first-line-h1 -->
@@ -188,4 +335,23 @@ OrionStar-Yi-34B-Chat 开源模型而导致的任何问题，包括但不限于
 
 <div align="center">
   <img src="./pics/wechat_group.jpg" alt="wechat" width="40%" />
-</div>
+</div>
+
+
+# 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/OrionStarAI/OrionStar-Yi-34B-Chat) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**72.87**|
+|ENEM Challenge (No Images)|    70.40|
+|BLUEX (No Images)         |    62.03|
+|OAB Exams                 |    50.66|
+|Assin2 RTE                |    91.71|
+|Assin2 STS                |    79.69|
+|FaQuAD NLI                |    78.40|
+|HateBR Binary             |    84.44|
+|PT Hate Speech Binary     |    65.91|
+|tweetSentBR               |    72.62|
+