Adding Evaluation Results

README.md

@@ -1,6 +1,7 @@
 ---
-language: 
-  - en
+language:
+- en
+license: mit
 tags:
 - llama2
 - llama-2
@@ -11,9 +12,111 @@ datasets:
 - Redpajama
 metrics:
 - MMLU
-license: mit
 widget:
-- text: "Q: What is the largest bird?\\nA:"
+- text: 'Q: What is the largest bird?\nA:'
+model-index:
+- name: LiteLlama-460M-1T
+  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: 24.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
+      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: 38.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
+      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: 25.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
+      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: 41.59
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
+      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: 50.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
+      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=ahxt/LiteLlama-460M-1T
+      name: Open LLM Leaderboard
 ---
 
 # LiteLlama: Reduced-Scale Llama
@@ -92,3 +195,17 @@ This model was developed by [Xiaotian Han](https://ahxt.github.io/) from Texas A
 
 
 
+
+# [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_ahxt__LiteLlama-460M-1T)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |30.16|
+|AI2 Reasoning Challenge (25-Shot)|24.83|
+|HellaSwag (10-Shot)              |38.39|
+|MMLU (5-Shot)                    |25.96|
+|TruthfulQA (0-shot)              |41.59|
+|Winogrande (5-shot)              |50.20|
+|GSM8k (5-shot)                   | 0.00|
+