Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
+language:
+- en
 license: llama2
 datasets:
 - garage-bAInd/Open-Platypus
 - Open-Orca/OpenOrca
 - totally-not-an-llm/EverythingLM-data-V2
-language:
-- en
+model-index:
+- name: PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+  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: 54.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+      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: 79.36
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+      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: 55.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+      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: 54.32
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+      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: 71.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+      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=TFLai/PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/SNX5IX0YqN_MUhUzdMjJc.png)
 
@@ -28,3 +131,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | Winogrande (5-shot)   | 71.11   |
 | GSM8K (5-shot)        | 0.0        |
 | DROP (3-shot)         | 20.49         |
+
+# [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_TFLai__PuddleJumper-Platypus2-13B-QLoRA-0.80-epoch)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.41|
+|AI2 Reasoning Challenge (25-Shot)|54.52|
+|HellaSwag (10-Shot)              |79.36|
+|MMLU (5-Shot)                    |55.15|
+|TruthfulQA (0-shot)              |54.32|
+|Winogrande (5-shot)              |71.11|
+|GSM8k (5-shot)                   | 0.00|
+