Adding Evaluation Results (#1)

- Adding Evaluation Results (1010f548087521f279e34efa9de18d8a58fc1f93)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,19 +1,120 @@
 ---
-base_model: mistralai/Mistral-7B-Instruct-v0.2
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- transformers
 datasets:
 - mwitiderrick/SwahiliAlpaca
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 inference: true
 model_type: mistral
-
 created_by: mwitiderrick
-tags:
-- transformers
-license: apache-2.0
-language:
-- en
-library_name: transformers
 pipeline_tag: text-generation
-          
+model-index:
+- name: SwahiliInstruct-v0.2
+  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: 55.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/SwahiliInstruct-v0.2
+      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: 78.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/SwahiliInstruct-v0.2
+      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: 50.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/SwahiliInstruct-v0.2
+      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: 57.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/SwahiliInstruct-v0.2
+      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: 73.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/SwahiliInstruct-v0.2
+      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: 11.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/SwahiliInstruct-v0.2
+      name: Open LLM Leaderboard
 ---
 # SwahiliInstruct-v0.2
 
@@ -51,3 +152,17 @@ Koroga mchanganyiko pamoja na mbegu za kikombe 1 1/2 za mtindi wenye jamii na ha
 4. Kando ya uwanja, changanya zaini ya yai 2
 """
 ```
+
+# [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_mwitiderrick__SwahiliInstruct-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |54.25|
+|AI2 Reasoning Challenge (25-Shot)|55.20|
+|HellaSwag (10-Shot)              |78.22|
+|MMLU (5-Shot)                    |50.30|
+|TruthfulQA (0-shot)              |57.08|
+|Winogrande (5-shot)              |73.24|
+|GSM8k (5-shot)                   |11.45|
+