Adding Evaluation Results (#9)

- Adding Evaluation Results (a60aad07abc583b39bb391aa01bb0564d276c92a)


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

README.md

@@ -1,10 +1,113 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - totally-not-an-llm/everything-sharegptformat-morecleaned
-language:
-- en
 pipeline_tag: text-generation
+model-index:
+- name: Marx-3B
+  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: 43.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
+      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: 72.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
+      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: 28.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
+      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: 39.09
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
+      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: 65.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
+      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: 1.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
+      name: Open LLM Leaderboard
 ---
 
 <a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
@@ -36,3 +139,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | TruthfulQA (0-shot)   | 39.09   |
 | Winogrande (5-shot)   | 65.59   |
 | GSM8K (5-shot)        | 1.29        |
+
+# [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_acrastt__Marx-3B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |41.71|
+|AI2 Reasoning Challenge (25-Shot)|43.17|
+|HellaSwag (10-Shot)              |72.68|
+|MMLU (5-Shot)                    |28.46|
+|TruthfulQA (0-shot)              |39.09|
+|Winogrande (5-shot)              |65.59|
+|GSM8k (5-shot)                   | 1.29|
+