Adding Evaluation Results

This is an automated PR created with https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,16 +1,111 @@
 ---
+language:
+- en
 license: other
-license_name: qwen
-license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
-datasets:
-- Magpie-Align/Magpie-Qwen2.5-Pro-300K-Filtered
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
 library_name: transformers
 tags:
 - generated_from_trainer
-language:
-- en
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+datasets:
+- Magpie-Align/Magpie-Qwen2.5-Pro-300K-Filtered
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
+model-index:
+- name: cybertron-v4-qw7B-MGS
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 62.64
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 37.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 27.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 8.05
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 13.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 38.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
+      name: Open LLM Leaderboard
 ---
 
 # cybertron-v4-qw7B-MGS
@@ -65,4 +160,17 @@ The following hyperparameters were used during training:
 - Transformers 4.45.2
 - Pytorch 2.3.0+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.1
+- Tokenizers 0.20.1
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__cybertron-v4-qw7B-MGS)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |31.21|
+|IFEval (0-Shot)    |62.64|
+|BBH (3-Shot)       |37.04|
+|MATH Lvl 5 (4-Shot)|27.72|
+|GPQA (0-shot)      | 8.05|
+|MuSR (0-shot)      |13.20|
+|MMLU-PRO (5-shot)  |38.59|
+