Adding Evaluation Results (#1)

- Adding Evaluation Results (ca07a2eb58135cc13a4b9eccac04d1feefc97a38)


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

README.md

@@ -8,6 +8,109 @@ datasets:
 - jondurbin/py-dpo-v0.1
 - Replete-AI/code_bagel_hermes-2.5
 - mlabonne/orpo-dpo-mix-40k
+model-index:
+- name: UNA-ThePitbull-21.4B-v2
+  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: 77.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-ThePitbull-21.4B-v2
+      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: 91.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-ThePitbull-21.4B-v2
+      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: 68.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-ThePitbull-21.4B-v2
+      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: 78.24
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-ThePitbull-21.4B-v2
+      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: 87.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-ThePitbull-21.4B-v2
+      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: 63.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-ThePitbull-21.4B-v2
+      name: Open LLM Leaderboard
 ---
 
 # UNA-ThePitbull 21.4B v2
@@ -109,4 +212,17 @@ If you use UNA models dont forget to cite:
   journal = {HuggingFace repository},
   howpublished = {\url{https://huggingface.co/fblgit/UNA-ThePitbull-21.4-v1}},
 }
-```
+```
+# [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_fblgit__UNA-ThePitbull-21.4B-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |77.82|
+|AI2 Reasoning Challenge (25-Shot)|77.73|
+|HellaSwag (10-Shot)              |91.79|
+|MMLU (5-Shot)                    |68.25|
+|TruthfulQA (0-shot)              |78.24|
+|Winogrande (5-shot)              |87.37|
+|GSM8k (5-shot)                   |63.53|
+