Adding Evaluation Results (#1)

- Adding Evaluation Results (39657e52d8b0067603fe3c7f505ef83b6a172ee2)


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

README.md

@@ -1,12 +1,114 @@
 ---
 license: apache-2.0
-base_model:
-- BarryFutureman/WildMarcoroni-Variant1-7B
-- nbeerbower/bruphin-delta
 tags:
 - mergekit
 - merge
-
+base_model:
+- BarryFutureman/WildMarcoroni-Variant1-7B
+- nbeerbower/bruphin-delta
+model-index:
+- name: bruphin-epsilon
+  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: 72.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
+      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: 88.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
+      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: 65.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
+      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: 66.95
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
+      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: 83.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
+      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: 70.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
+      name: Open LLM Leaderboard
 ---
 # bruphin-epsilon
 
@@ -45,3 +147,17 @@ parameters:
 dtype: bfloat16
 
 ```
+
+# [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_nbeerbower__bruphin-epsilon)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.42|
+|AI2 Reasoning Challenge (25-Shot)|72.10|
+|HellaSwag (10-Shot)              |88.09|
+|MMLU (5-Shot)                    |65.04|
+|TruthfulQA (0-shot)              |66.95|
+|Winogrande (5-shot)              |83.82|
+|GSM8k (5-shot)                   |70.51|
+