Adding Evaluation Results

README.md

@@ -1,6 +1,109 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
+model-index:
+- name: Mistral-Instruct-Ukrainian-SFT
+  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: 57.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
+      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: 83.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
+      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: 60.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
+      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: 54.14
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
+      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: 77.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
+      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: 39.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
+      name: Open LLM Leaderboard
 ---
 
 # Model card for Mistral-Instruct-Ukrainian-SFT
@@ -59,4 +162,17 @@ print(outputs[0]["generated_text"])
 
 ## Author
 
-Radu Chivereanu
+Radu Chivereanu
+# [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_Radu1999__Mistral-Instruct-Ukrainian-SFT)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.17|
+|AI2 Reasoning Challenge (25-Shot)|57.85|
+|HellaSwag (10-Shot)              |83.12|
+|MMLU (5-Shot)                    |60.95|
+|TruthfulQA (0-shot)              |54.14|
+|Winogrande (5-shot)              |77.51|
+|GSM8k (5-shot)                   |39.42|
+