Adding Evaluation Results (#1)

- Adding Evaluation Results (a711cb2f080c9a5ca02ca331dc7887424a225e2b)


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

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-1M-v0.1
-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-1M-v0.1
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
+model-index:
+- name: cybertron-v4-qw7B-UNAMGS
+  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: 60.84
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-UNAMGS
+      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: 37.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-UNAMGS
+      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: 29.91
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-UNAMGS
+      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: 10.85
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-UNAMGS
+      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: 12.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-UNAMGS
+      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: 38.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-UNAMGS
+      name: Open LLM Leaderboard
 ---
 
 # cybertron-v4-qw7B-UNAMGS
@@ -124,3 +219,17 @@ The following hyperparameters were used during training:
       year={2024}
 }
 ```
+
+# [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-UNAMGS)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |31.82|
+|IFEval (0-Shot)    |60.84|
+|BBH (3-Shot)       |37.71|
+|MATH Lvl 5 (4-Shot)|29.91|
+|GPQA (0-shot)      |10.85|
+|MuSR (0-shot)      |12.69|
+|MMLU-PRO (5-shot)  |38.89|
+