Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
+language:
+- en
+- ta
 license: other
-license_name: gemma-terms-of-use
-license_link: https://ai.google.dev/gemma/terms
 datasets:
 - vicgalle/alpaca-gpt4
 - abhinand/tamil-alpaca
-language:
-- en
-- ta
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
 base_model: abhinand/gemma-2b-tamil
+model-index:
+- name: gemma-2b-it-tamil-v0.1-alpha
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 50.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 71.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 39.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 42.63
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 16.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
+      name: Open LLM Leaderboard
 ---
 
 # Gemma 2B Tamil v0.1 Alpha [Experimental Release]
@@ -89,4 +192,17 @@ Get to know the creators behind this innovative model and follow their contribut
 
 - [Abhinand Balachandran](https://www.linkedin.com/in/abhinand-05/)
 
-We hope this model serves as a valuable tool in your NLP toolkit and look forward to seeing the advancements it will enable in the understanding and generation of the Tamil language.
+We hope this model serves as a valuable tool in your NLP toolkit and look forward to seeing the advancements it will enable in the understanding and generation of the Tamil language.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abhinand__gemma-2b-it-tamil-v0.1-alpha)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.60|
+|AI2 Reasoning Challenge (25-Shot)|50.09|
+|HellaSwag (10-Shot)              |71.41|
+|MMLU (5-Shot)                    |39.94|
+|TruthfulQA (0-shot)              |42.63|
+|Winogrande (5-shot)              |64.96|
+|GSM8k (5-shot)                   |16.60|
+