Adding the Open Portuguese LLM Leaderboard Evaluation Results

README.md

@@ -7,11 +7,158 @@ tags:
 - LoRA
 - Llama
 - Stanford-Alpaca
+base_model: decapoda-research/llama-7b-hf
 datasets:
 - dominguesm/alpaca-data-pt-br
 thumbnail: https://huggingface.co/dominguesm/alpaca-lora-ptbr-7b/resolve/main/assets/alpaca_br_juliet_2.jpg
 inference: false
-base_model: decapoda-research/llama-7b-hf
+model-index:
+- name: alpaca-lora-ptbr-7b
+  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: 22.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 23.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 26.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 33.7
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 18.17
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 56.27
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 33.33
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 22.99
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      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: 46.95
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=RogerioPiazzon/alpaca-lora-ptbr-7b
+      name: Open Portuguese LLM Leaderboard
 ---
 
 ## 🦙🇧🇷 Alpaca-LoRA-PTBR: Low-Rank LLaMA Instruct-Tuning
@@ -222,4 +369,23 @@ LLaMA is a foundational model, and as such, it should not be used for downstream
 ## References
 
 * Workout descriptions and script based on work done by [Eric J. Wang](https://github.com/tloen/alpaca-lora)
-* Training data based on original [Stanford Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html) work
+* Training data based on original [Stanford Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html) work
+
+
+# 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/RogerioPiazzon/alpaca-lora-ptbr-7b) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
+
+|          Metric          |  Value  |
+|--------------------------|---------|
+|Average                   |**31.53**|
+|ENEM Challenge (No Images)|    22.32|
+|BLUEX (No Images)         |    23.50|
+|OAB Exams                 |    26.51|
+|Assin2 RTE                |    33.70|
+|Assin2 STS                |    18.17|
+|FaQuAD NLI                |    56.27|
+|HateBR Binary             |    33.33|
+|PT Hate Speech Binary     |    22.99|
+|tweetSentBR               |    46.95|
+