Adding Evaluation Results (#5)

- Adding Evaluation Results (6abfd66bc7d3c2fc31bdd0eae7c04d69061dd50a)


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

README.md

@@ -1,10 +1,113 @@
 ---
-license: apache-2.0
-datasets:
-- totally-not-an-llm/EverythingLM-data-V2-sharegpt
 language:
 - en
+license: apache-2.0
 library_name: transformers
+datasets:
+- totally-not-an-llm/EverythingLM-data-V2-sharegpt
+model-index:
+- name: Marx-3B-V2
+  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: 44.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B-V2
+      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: 72.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B-V2
+      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: 27.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B-V2
+      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: 39.92
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B-V2
+      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: 66.54
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B-V2
+      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: 1.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B-V2
+      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>
 
@@ -20,3 +123,17 @@ Prompt template:
 ```
 q4_1 GGML quant available [here](https://huggingface.co/NikolayKozloff/Marx-3B-V2/).</br>
 q4_1 GGUF quant available [here]( https://huggingface.co/NikolayKozloff/Marx-3B-V2-GGUF/).
+
+# [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-V2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |42.08|
+|AI2 Reasoning Challenge (25-Shot)|44.03|
+|HellaSwag (10-Shot)              |72.92|
+|MMLU (5-Shot)                    |27.84|
+|TruthfulQA (0-shot)              |39.92|
+|Winogrande (5-shot)              |66.54|
+|GSM8k (5-shot)                   | 1.21|
+