Adding Evaluation Results

README.md

@@ -1,13 +1,17 @@
 ---
-library_name: transformers
-base_model: HuggingFaceH4/zephyr-7b-beta
-license: mit
 language:
 - ru
 - en
+license: mit
+library_name: transformers
 tags:
 - python
 - code
+datasets:
+- MexIvanov/Vezora-Tested-22k-Python-Alpaca-ru
+- MexIvanov/CodeExercise-Python-27k-ru
+- zelkame/ru-stackoverflow-py
+base_model: HuggingFaceH4/zephyr-7b-beta
 pipeline_tag: conversational
 model-index:
 - name: zephyr-python-ru-merged
@@ -18,76 +22,172 @@ model-index:
       name: gsm8k
       type: gsm8k
     metrics:
-    - name: Grade School Math 8K (5-Shot)
-      type: Grade School Math 8K (5-Shot)
+    - type: Grade School Math 8K (5-Shot)
       value: 32.52
+      name: Grade School Math 8K (5-Shot)
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
   - task:
       type: text-generation
     dataset:
       name: ai2_arc
       type: ai2_arc
     metrics:
-    - name: AI2 Reasoning Challenge (25-Shot)
-      type: AI2 Reasoning Challenge (25-Shot)
+    - type: AI2 Reasoning Challenge (25-Shot)
       value: 56.06
+      name: AI2 Reasoning Challenge (25-Shot)
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
   - task:
       type: text-generation
     dataset:
       name: HellaSwag
       type: HellaSwag
     metrics:
-    - name: HellaSwag (10-Shot)
-      type: HellaSwag (10-Shot)
+    - type: HellaSwag (10-Shot)
       value: 82.06
+      name: HellaSwag (10-Shot)
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
   - task:
       type: text-generation
     dataset:
       name: MMLU
       type: MMLU
     metrics:
-    - name: MMLU (5-Shot)
-      type: MMLU (5-Shot)
+    - type: MMLU (5-Shot)
       value: 60.02
+      name: MMLU (5-Shot)
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
   - task:
       type: text-generation
     dataset:
       name: truthfulqa
       type: truthfulqa
     metrics:
-    - name: truthfulqa:mc (0-Shot)
-      type: truthfulqa:mc (0-Shot)
+    - type: truthfulqa:mc (0-Shot)
       value: 52.81
+      name: truthfulqa:mc (0-Shot)
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+      name: Open LLM Leaderboard
   - task:
       type: text-generation
     dataset:
       name: winogrande
       type: winogrande
     metrics:
-    - name: winogrande (5-Shot)
-      type: winogrande (5-Shot)
+    - type: winogrande (5-Shot)
       value: 76.95
+      name: winogrande (5-Shot)
     source:
-      name: Open LLM Leaderboard
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-datasets:
-- MexIvanov/Vezora-Tested-22k-Python-Alpaca-ru
-- MexIvanov/CodeExercise-Python-27k-ru
-- zelkame/ru-stackoverflow-py
+      name: Open LLM Leaderboard
+  - 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: 56.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
+      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: 82.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
+      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: 60.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
+      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: 52.81
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
+      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: 76.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
+      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: 32.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -188,4 +288,17 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.6.2
+- PEFT 0.6.2
+# [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_MexIvanov__zephyr-python-ru-merged)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.10|
+|AI2 Reasoning Challenge (25-Shot)|56.06|
+|HellaSwag (10-Shot)              |82.06|
+|MMLU (5-Shot)                    |60.20|
+|TruthfulQA (0-shot)              |52.81|
+|Winogrande (5-shot)              |76.95|
+|GSM8k (5-shot)                   |32.52|
+