Adding Evaluation Results (#3)

- Adding Evaluation Results (6854b359d34cd6aeccf5b271ded1583f8a07b7ed)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,8 +1,7 @@
 ---
-language: 
-  - "en" 
-metrics:
-- code_eval
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - code
@@ -10,7 +9,111 @@ tags:
 datasets:
 - andersonbcdefg/synthetic_retrieval_tasks
 - ise-uiuc/Magicoder-Evol-Instruct-110K
-license: "apache-2.0"
+metrics:
+- code_eval
+model-index:
+- name: moe-x33
+  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: 26.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 26.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 24.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 51.14
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 50.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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=senseable/moe-x33
+      name: Open LLM Leaderboard
 ---
 
 
@@ -66,4 +169,17 @@ print("Generated Code:\n", decoded_output)
 
 ---
 license: apache-2.0
----
+---
+# [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_senseable__moe-x33)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |29.95|
+|AI2 Reasoning Challenge (25-Shot)|26.19|
+|HellaSwag (10-Shot)              |26.44|
+|MMLU (5-Shot)                    |24.93|
+|TruthfulQA (0-shot)              |51.14|
+|Winogrande (5-shot)              |50.99|
+|GSM8k (5-shot)                   | 0.00|
+