Adding Evaluation Results (#8)

- Adding Evaluation Results (f56a53d6eaaf0251ee8d3690f07490eb910e29e6)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,8 +1,7 @@
 ---
 language:
 - en
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
-pipeline_tag: text-generation
+license: other
 tags:
 - facebook
 - meta
@@ -11,9 +10,113 @@ tags:
 - llama-3
 - moe
 - code
-license: other
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+pipeline_tag: text-generation
 license_name: llama3
 license_link: LICENSE
+model-index:
+- name: Llama-3-Aplite-Instruct-4x8B-MoE
+  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: 61.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
+      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: 81.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
+      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: 67.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
+      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: 51.87
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
+      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: 77.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
+      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: 61.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
+      name: Open LLM Leaderboard
 ---
 
 
@@ -137,4 +240,17 @@ If you'd like to discuss potential collaborations or applications, feel free to
 
 **Meta Llama 3 is
 licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
-Reserved.**
+Reserved.**
+# [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_raincandy-u__Llama-3-Aplite-Instruct-4x8B-MoE)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.99|
+|AI2 Reasoning Challenge (25-Shot)|61.86|
+|HellaSwag (10-Shot)              |81.08|
+|MMLU (5-Shot)                    |67.47|
+|TruthfulQA (0-shot)              |51.87|
+|Winogrande (5-shot)              |77.82|
+|GSM8k (5-shot)                   |61.87|
+