Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
+license: other
+metrics:
+- accuracy
 base_model: Mihaiii/Pallas-0.5
 inference: false
-license: other
 license_name: yi-license
 license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
-metrics:
-- accuracy
+model-index:
+- name: Pallas-0.5-frankenmerge
+  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: 61.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
+      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: 80.36
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
+      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: 67.62
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
+      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: 54.07
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
+      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: 77.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
+      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: 24.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
+      name: Open LLM Leaderboard
 ---
 
 This is a frankenmerge of [Mihaiii/Pallas-0.5](https://huggingface.co/Mihaiii/Pallas-0.5) .
@@ -48,3 +151,17 @@ Quants:
 [TheBloke/Pallas-0.5-frankenmerge-GPTQ](https://huggingface.co/TheBloke/Pallas-0.5-frankenmerge-GPTQ)
 
 [TheBloke/Pallas-0.5-frankenmerge-AWQ](https://huggingface.co/TheBloke/Pallas-0.5-frankenmerge-AWQ)
+
+# [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_Mihaiii__Pallas-0.5-frankenmerge)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.95|
+|AI2 Reasoning Challenge (25-Shot)|61.77|
+|HellaSwag (10-Shot)              |80.36|
+|MMLU (5-Shot)                    |67.62|
+|TruthfulQA (0-shot)              |54.07|
+|Winogrande (5-shot)              |77.74|
+|GSM8k (5-shot)                   |24.11|
+