Adding Evaluation Results (#1)

- Adding Evaluation Results (fd23426d405edccf288e2a99803b4c338aeb61ec)


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

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- eren23/dpo-binarized-NeutrixOmnibe-7B
-- Gille/StrangeMerges_21-7B-slerp
+license: cc-by-nc-4.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: cc-by-nc-4.0
+base_model:
+- eren23/dpo-binarized-NeutrixOmnibe-7B
+- Gille/StrangeMerges_21-7B-slerp
+model-index:
+- name: AlloyIngot
+  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: 73.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/AlloyIngot
+      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: 89.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/AlloyIngot
+      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: 64.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/AlloyIngot
+      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: 75.12
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/AlloyIngot
+      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: 85.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/AlloyIngot
+      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: 69.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/AlloyIngot
+      name: Open LLM Leaderboard
 ---
 # merged
 
@@ -50,4 +153,17 @@ slices:
     model:
       model:
         path: Gille/StrangeMerges_21-7B-slerp
-```
+```
+# [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_nlpguy__AlloyIngot)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |76.20|
+|AI2 Reasoning Challenge (25-Shot)|73.98|
+|HellaSwag (10-Shot)              |89.05|
+|MMLU (5-Shot)                    |64.83|
+|TruthfulQA (0-shot)              |75.12|
+|Winogrande (5-shot)              |85.08|
+|GSM8k (5-shot)                   |69.14|
+