Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
 language:
 - en
+license: creativeml-openrail-m
 datasets:
 - Anthropic/hh-rlhf
-license: creativeml-openrail-m
+model-index:
+- name: babyllama-v0.6
+  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: 36.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/babyllama-v0.6
+      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: 61.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/babyllama-v0.6
+      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: 25.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/babyllama-v0.6
+      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: 35.84
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/babyllama-v0.6
+      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: 61.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/babyllama-v0.6
+      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: 1.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/babyllama-v0.6
+      name: Open LLM Leaderboard
 ---
 # Model Card for BabyLlama v0.6
 
@@ -93,4 +196,17 @@ TinyLlama 1.1b model
 Anthropic rlhf dataset
 
 ## Version History
-- **v0.5:** Enhanced for creativity and humor in conversations, diverging from strict instruction adherence to offer a unique conversational experience.
+- **v0.5:** Enhanced for creativity and humor in conversations, diverging from strict instruction adherence to offer a unique conversational experience.
+# [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_kevin009__babyllama-v0.6)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.92|
+|AI2 Reasoning Challenge (25-Shot)|36.09|
+|HellaSwag (10-Shot)              |61.59|
+|MMLU (5-Shot)                    |25.37|
+|TruthfulQA (0-shot)              |35.84|
+|Winogrande (5-shot)              |61.01|
+|GSM8k (5-shot)                   | 1.59|
+