Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -1,7 +1,5 @@
 ---
 license: other
-license_name: yi-license
-license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
 datasets:
 - ai2_arc
 - unalignment/spicy-3.1
@@ -27,11 +25,160 @@ datasets:
 - Intel/orca_dpo_pairs
 - unalignment/toxic-dpo-v0.1
 - jondurbin/truthy-dpo-v0.1
-- allenai/ultrafeedback_binarized_cleaned 
+- allenai/ultrafeedback_binarized_cleaned
 - Squish42/bluemoon-fandom-1-1-rp-cleaned
 - LDJnr/Capybara
 - JULIELab/EmoBank
 - kingbri/PIPPA-shareGPT
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+model-index:
+- name: bagel-dpo-34b-v0.2
+  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: 71.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 66.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 53.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 91.53
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 78.93
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 83.86
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 72.79
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 72.41
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      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: 71.99
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=jondurbin/bagel-dpo-34b-v0.2
+      name: Open Portuguese LLM Leaderboard
 ---
 
 # A bagel, with everything
@@ -227,4 +374,23 @@ To help me with the OpenAI/compute costs:
 
 - https://bmc.link/jondurbin
 - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
-- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
+- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
+
+
+# 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/jondurbin/bagel-dpo-34b-v0.2) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**73.71**|
+|ENEM Challenge (No Images)|    71.94|
+|BLUEX (No Images)         |    66.90|
+|OAB Exams                 |    53.03|
+|Assin2 RTE                |    91.53|
+|Assin2 STS                |    78.93|
+|FaQuAD NLI                |    83.86|
+|HateBR Binary             |    72.79|
+|PT Hate Speech Binary     |    72.41|
+|tweetSentBR               |    71.99|
+