Adding Evaluation Results (#1)

- Adding Evaluation Results (9c40a54646b92cc3e1959fff18fedb48b723dd63)


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

README.md

@@ -1,15 +1,110 @@
 ---
+license: llama3
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - flammenai/Mahou-1.2-llama3-8B
 - lemon07r/Llama-3-RedMagic2-8B
 - lemon07r/Lllama-3-RedElixir-8B
 - NousResearch/Meta-Llama-3-8B
 - nbeerbower/llama-3-spicy-abliterated-stella-8B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: llama3
+model-index:
+- name: Llama-3-RedMagic4-8B
+  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: 48.64
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Llama-3-RedMagic4-8B
+      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: 19.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Llama-3-RedMagic4-8B
+      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: 8.31
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Llama-3-RedMagic4-8B
+      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: 5.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Llama-3-RedMagic4-8B
+      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: 4.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Llama-3-RedMagic4-8B
+      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: 29.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lemon07r/Llama-3-RedMagic4-8B
+      name: Open LLM Leaderboard
 ---
 # Llama-3-RedMagic4-8B
 
@@ -48,4 +143,17 @@ slices:
     model: flammenai/Mahou-1.2-llama3-8B
   - layer_range: [0, 32]
     model: NousResearch/Meta-Llama-3-8B
-```
+```
+# [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_lemon07r__Llama-3-RedMagic4-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.32|
+|IFEval (0-Shot)    |48.64|
+|BBH (3-Shot)       |19.48|
+|MATH Lvl 5 (4-Shot)| 8.31|
+|GPQA (0-shot)      | 5.37|
+|MuSR (0-shot)      | 4.38|
+|MMLU-PRO (5-shot)  |29.73|
+