Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
+language:
+- ru
 license: apache-2.0
 datasets:
 - 0x7194633/fialka-v3-data
-language:
-- ru
 pipeline_tag: text-generation
+model-index:
+- name: fialka-13B-v3
+  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: 30.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=0x7194633/fialka-13B-v3
+      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: 48.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=0x7194633/fialka-13B-v3
+      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: 26.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=0x7194633/fialka-13B-v3
+      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: 40.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=0x7194633/fialka-13B-v3
+      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: 59.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=0x7194633/fialka-13B-v3
+      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: 1.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=0x7194633/fialka-13B-v3
+      name: Open LLM Leaderboard
 ---
 # Fialka v3.0 13B
 
@@ -19,4 +122,17 @@ The model has a query format as in zephyr.
 <|assistant|>
 Мем (англ. meme) — это единица культурной информации, которая распространяется в социальных сетях и других онлайн-платформах с помощью цифровых технологий или через физический контакт. Мемы могут быть связаны между собой тематически или иметь общие черты, такие как использование определенных слов или фраз для создания определенного настроения или выражения эмоций. Они также могут содержать информацию о культуре, истории или науке, которую можно использовать для обучения новым вещам или расширения кругозора.
 ```
-Check out the [space](https://huggingface.co/spaces/0x7194633/fialka) to use the model in UI without downloading.
+Check out the [space](https://huggingface.co/spaces/0x7194633/fialka) to use the model in UI without downloading.
+# [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_0x7194633__fialka-13B-v3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |34.58|
+|AI2 Reasoning Challenge (25-Shot)|30.97|
+|HellaSwag (10-Shot)              |48.83|
+|MMLU (5-Shot)                    |26.36|
+|TruthfulQA (0-shot)              |40.58|
+|Winogrande (5-shot)              |59.43|
+|GSM8k (5-shot)                   | 1.29|
+