Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
-license: apache-2.0
-datasets:
-- Open-Orca/OpenOrca
 language:
 - en
+license: apache-2.0
 library_name: transformers
-pipeline_tag: question-answering
+datasets:
+- Open-Orca/OpenOrca
 metrics:
 - accuracy
+pipeline_tag: question-answering
+model-index:
+- name: YetAnother_Open-Llama-3B-LoRA-OpenOrca
+  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: 25.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca
+      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: 25.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca
+      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: 24.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca
+      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: 0.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca
+      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: 50.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca
+      name: Open LLM Leaderboard
 ---
 ## Model Details
 
@@ -103,4 +206,17 @@ Accuracy
 
 ## Model Card Authors and Contact
 
-[Andron00e](https://github.com/Andron00e)
+[Andron00e](https://github.com/Andron00e)
+# [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_Andron00e__YetAnother_Open-Llama-3B-LoRA-OpenOrca)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |21.20|
+|AI2 Reasoning Challenge (25-Shot)|25.94|
+|HellaSwag (10-Shot)              |25.76|
+|MMLU (5-Shot)                    |24.65|
+|TruthfulQA (0-shot)              | 0.00|
+|Winogrande (5-shot)              |50.83|
+|GSM8k (5-shot)                   | 0.00|
+