Adding Evaluation Results (#2)

- Adding Evaluation Results (092a9226ab3cbde361701f1963ba157b2b8d0dba)


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

README.md

@@ -6,6 +6,109 @@ tags:
 - lazymergekit
 - AI-B/UTENA-7B-UNA-V2
 - AI-B/UTENA-7B-NSFW-V2
+model-index:
+- name: UTENA-7B-V3
+  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: 65.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 85.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 64.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 53.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 80.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      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: 54.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
+      name: Open LLM Leaderboard
 ---
 
 # UTENA-7B-V3
@@ -38,4 +141,17 @@ dtype: bfloat16
 
 ## Quanitized Models
 
-[UTENA-7B-V3-GGUF](https://huggingface.co/s3nh/UTENA-7B-V3-GGUF)
+[UTENA-7B-V3-GGUF](https://huggingface.co/s3nh/UTENA-7B-V3-GGUF)
+# [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_AI-B__UTENA-7B-V3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.42|
+|AI2 Reasoning Challenge (25-Shot)|65.96|
+|HellaSwag (10-Shot)              |85.70|
+|MMLU (5-Shot)                    |64.72|
+|TruthfulQA (0-shot)              |53.64|
+|Winogrande (5-shot)              |80.27|
+|GSM8k (5-shot)                   |54.21|
+