Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
-license: cc-by-nc-nd-4.0
 language:
-  - en
+- en
+license: cc-by-nc-nd-4.0
 library_name: transformers
-pipeline_tag: text-generation
 tags:
-  - starling
-  - mistral
-  - llama-2
+- starling
+- mistral
+- llama-2
+pipeline_tag: text-generation
+model-index:
+- name: Velara-11B-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: 63.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara-11B-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: 85.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara-11B-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: 63.62
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara-11B-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: 58.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara-11B-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: 77.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara-11B-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: 43.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara-11B-V2
+      name: Open LLM Leaderboard
 ---
 
 <h1 style="font-size: 36px;">Velara-11b-v2</h1>
@@ -66,3 +169,17 @@ PENDING
 
 # Training Data:
 PENDING
+
+# [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_Delcos__Velara-11B-V2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |65.55|
+|AI2 Reasoning Challenge (25-Shot)|63.82|
+|HellaSwag (10-Shot)              |85.85|
+|MMLU (5-Shot)                    |63.62|
+|TruthfulQA (0-shot)              |58.83|
+|Winogrande (5-shot)              |77.82|
+|GSM8k (5-shot)                   |43.37|
+