Adding Evaluation Results

README.md

@@ -1,10 +1,9 @@
 ---
-license: apache-2.0
 language:
 - en
 - de
+license: apache-2.0
 library_name: transformers
-pipeline_tag: text-generation
 tags:
 - finetune
 - sft
@@ -13,6 +12,110 @@ tags:
 - augmentation
 - german
 - english
+pipeline_tag: text-generation
+model-index:
+- name: SauerkrautLM-7b-LaserChat
+  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: 67.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-7b-LaserChat
+      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: 83.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-7b-LaserChat
+      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: 64.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-7b-LaserChat
+      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: 56.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-7b-LaserChat
+      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: 80.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-7b-LaserChat
+      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: 68.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-7b-LaserChat
+      name: Open LLM Leaderboard
 ---
 ![SauerkrautLM](https://vago-solutions.de/wp-content/uploads/2024/02/Sauerkraut_Laserchat.png "SauerkrautLM-7b-LaserChat")
 ## VAGO solutions SauerkrautLM-7b-LaserChat
@@ -117,3 +220,17 @@ We are also keenly seeking support and investment for our startups, VAGO solutio
 
 ## Acknowledgement
 Many thanks to [openchat](https://huggingface.co/openchat) for providing such valuable model to the Open-Source community
+
+# [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_VAGOsolutions__SauerkrautLM-7b-LaserChat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.32|
+|AI2 Reasoning Challenge (25-Shot)|67.58|
+|HellaSwag (10-Shot)              |83.58|
+|MMLU (5-Shot)                    |64.93|
+|TruthfulQA (0-shot)              |56.08|
+|Winogrande (5-shot)              |80.90|
+|GSM8k (5-shot)                   |68.84|
+