Adding Evaluation Results

README.md

@@ -1,9 +1,13 @@
 ---
+license: other
+tags:
+- orca
+- orca2
+- microsoft
+model_name: Orca 2 13B
 base_model: microsoft/Orca-2-13b
 inference: false
-license: other
 model_creator: Microsoft
-model_name: Orca 2 13B
 model_type: llama
 pipeline_tag: text-generation
 prompt_template: '<|im_start|>system
@@ -18,10 +22,109 @@ prompt_template: '<|im_start|>system
 
   '
 quantized_by: TheBloke
-tags:
-- orca
-- orca2
-- microsoft
+model-index:
+- name: Orca-2-13B-GPTQ
+  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: 59.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Orca-2-13B-GPTQ
+      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: 79.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Orca-2-13B-GPTQ
+      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: 59.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Orca-2-13B-GPTQ
+      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: 55.14
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Orca-2-13B-GPTQ
+      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: 76.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Orca-2-13B-GPTQ
+      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: 15.54
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Orca-2-13B-GPTQ
+      name: Open LLM Leaderboard
 ---
 <!-- markdownlint-disable MD041 -->
 
@@ -613,3 +716,17 @@ print(final_output)
       primaryClass={cs.AI}
 }
 ```
+
+# [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_TheBloke__Orca-2-13B-GPTQ)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.60|
+|AI2 Reasoning Challenge (25-Shot)|59.81|
+|HellaSwag (10-Shot)              |79.12|
+|MMLU (5-Shot)                    |59.35|
+|TruthfulQA (0-shot)              |55.14|
+|Winogrande (5-shot)              |76.64|
+|GSM8k (5-shot)                   |15.54|
+