Adding Evaluation Results (#1)

- Adding Evaluation Results (21e8ab8cd2312f36cb6e742d4968730944a256b4)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,6 +1,5 @@
 ---
 license: cc-by-nc-4.0
-base_model: mlabonne/Beagle14-7B
 tags:
 - merge
 - mergekit
@@ -9,6 +8,110 @@ tags:
 - rlhf
 - rlaif
 - distilabel
+base_model: mlabonne/Beagle14-7B
+model-index:
+- name: DistilabelBeagle14-7B
+  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: 71.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/DistilabelBeagle14-7B
+      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: 87.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/DistilabelBeagle14-7B
+      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: 61.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/DistilabelBeagle14-7B
+      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: 68.91
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/DistilabelBeagle14-7B
+      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: 80.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/DistilabelBeagle14-7B
+      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: 36.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/DistilabelBeagle14-7B
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -203,3 +306,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 
 
+
+# [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_argilla__DistilabelBeagle14-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.52|
+|AI2 Reasoning Challenge (25-Shot)|71.08|
+|HellaSwag (10-Shot)              |87.00|
+|MMLU (5-Shot)                    |61.27|
+|TruthfulQA (0-shot)              |68.91|
+|Winogrande (5-shot)              |80.74|
+|GSM8k (5-shot)                   |36.09|
+