Adding Evaluation Results

README.md

@@ -1,18 +1,121 @@
 ---
-library_name: peft
-base_model: HuggingFaceH4/zephyr-7b-beta
-license: mit
 language:
 - ru
 - en
+license: mit
+library_name: peft
 tags:
 - python
 - code
-pipeline_tag: conversational
 datasets:
 - zelkame/ru-stackoverflow-py
 - MexIvanov/Vezora-Tested-22k-Python-Alpaca-ru
 - MexIvanov/CodeExercise-Python-27k-ru
+base_model: HuggingFaceH4/zephyr-7b-beta
+pipeline_tag: conversational
+model-index:
+- name: zephyr-python-ru
+  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: 56.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru
+      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: 82.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru
+      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: 60.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru
+      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: 52.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru
+      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: 76.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru
+      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
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -224,4 +327,17 @@ 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)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.08|
+|AI2 Reasoning Challenge (25-Shot)|56.14|
+|HellaSwag (10-Shot)              |82.03|
+|MMLU (5-Shot)                    |60.18|
+|TruthfulQA (0-shot)              |52.80|
+|Winogrande (5-shot)              |76.80|
+|GSM8k (5-shot)                   |32.52|
+