Adding Evaluation Results (#3)

- Adding Evaluation Results (c932fe2502cd59e1b2e67d0e02e13d12fc0d634c)


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

README.md

@@ -1,12 +1,115 @@
 ---
 license: other
-license_name: gemma-terms-of-use
-license_link: https://ai.google.dev/gemma/terms
 datasets:
 - Thermostatic/flowers
 - jondurbin/truthy-dpo-v0.1
 - Intel/orca_dpo_pairs
 - glaiveai/glaive-function-calling-v2
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+model-index:
+- name: gemma-orchid-7b-dpo
+  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: 62.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/gemma-orchid-7b-dpo
+      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: 80.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/gemma-orchid-7b-dpo
+      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: 61.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/gemma-orchid-7b-dpo
+      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: 53.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/gemma-orchid-7b-dpo
+      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: 77.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/gemma-orchid-7b-dpo
+      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: 50.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/gemma-orchid-7b-dpo
+      name: Open LLM Leaderboard
 ---
 
 # Gemma Orchid 7b
@@ -168,4 +271,17 @@ In progress
 
 ## ExLlamaV2
 
-Available [here](https://huggingface.co/bartowski/gemma-orchid-7b-dpo-exl2)
+Available [here](https://huggingface.co/bartowski/gemma-orchid-7b-dpo-exl2)
+# [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_macadeliccc__gemma-orchid-7b-dpo)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.37|
+|AI2 Reasoning Challenge (25-Shot)|62.88|
+|HellaSwag (10-Shot)              |80.95|
+|MMLU (5-Shot)                    |61.41|
+|TruthfulQA (0-shot)              |53.27|
+|Winogrande (5-shot)              |77.51|
+|GSM8k (5-shot)                   |50.19|
+