Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
-license: apache-2.0
-datasets:
-- LeoLM/OpenSchnabeltier
 language:
 - de
-pipeline_tag: conversational
+license: apache-2.0
 tags:
 - hermeo
 - laser
+datasets:
+- LeoLM/OpenSchnabeltier
+pipeline_tag: conversational
+model-index:
+- name: germeo-7b-laser
+  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: 60.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aari1995/germeo-7b-laser
+      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: 82.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aari1995/germeo-7b-laser
+      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: 60.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aari1995/germeo-7b-laser
+      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: 53.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aari1995/germeo-7b-laser
+      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: 75.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aari1995/germeo-7b-laser
+      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: 43.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aari1995/germeo-7b-laser
+      name: Open LLM Leaderboard
 ---
 
 (Evaluation WIP)
@@ -93,4 +196,17 @@ Even though the model does not generate English text without being explicitly as
 | mistral-7b                         |   **0.635** |     **0.832** |        0.607 |   **0.691** |
 | leolm-mistral-hessianai-7b         |       0.550 |         0.777 |        0.518 |       0.615 |
 | hermeo-7b                          |       0.601 |         0.821 |    **0.620** |       0.681 |
-| germeo-7b-laser (this model)       |       0.601 |         0.828 |        0.608 |       0.679 |
+| germeo-7b-laser (this model)       |       0.601 |         0.828 |        0.608 |       0.679 |
+# [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_aari1995__germeo-7b-laser)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.82|
+|AI2 Reasoning Challenge (25-Shot)|60.75|
+|HellaSwag (10-Shot)              |82.81|
+|MMLU (5-Shot)                    |60.57|
+|TruthfulQA (0-shot)              |53.83|
+|Winogrande (5-shot)              |75.61|
+|GSM8k (5-shot)                   |43.37|
+