Adding Evaluation Results (#1)

- Adding Evaluation Results (7ae01ff25710a4b7458c25cb6d745547eefddb62)

README.md

@@ -1,15 +1,8 @@
 ---
-base_model:
-- meta-llama/Llama-3.2-3B
-- bunnycore/Llama-3.2-3B-Mix-Skill
-- bunnycore/Llama-3.2-3B-Sci-Think
-- FuseAI/FuseChat-Llama-3.2-3B-Instruct
-- theprint/ReWiz-Llama-3.2-3B
 language:
 - en
-library_name: transformers
 license: llama3.2
-pipeline_tag: text-generation
+library_name: transformers
 tags:
 - facebook
 - meta
@@ -20,6 +13,108 @@ tags:
 - merge
 - chat
 - moonride
+base_model:
+- meta-llama/Llama-3.2-3B
+- bunnycore/Llama-3.2-3B-Mix-Skill
+- bunnycore/Llama-3.2-3B-Sci-Think
+- FuseAI/FuseChat-Llama-3.2-3B-Instruct
+- theprint/ReWiz-Llama-3.2-3B
+pipeline_tag: text-generation
+model-index:
+- name: Llama-3.2-3B-Khelavaster
+  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: 49.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
+      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: 22.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
+      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: 16.16
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
+      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: 3.69
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
+      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: 5.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
+      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: 23.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MoonRide/Llama-3.2-3B-Khelavaster
+      name: Open LLM Leaderboard
 ---
 <img src="https://huggingface.co/MoonRide/Llama-3.2-3B-Khelavaster/resolve/main/Khelavaster.jpg">
 
@@ -60,3 +155,17 @@ dtype: float32
 out_dtype: float16
 
 ```
+
+# [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/MoonRide__Llama-3.2-3B-Khelavaster-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.14|
+|IFEval (0-Shot)    |49.25|
+|BBH (3-Shot)       |22.69|
+|MATH Lvl 5 (4-Shot)|16.16|
+|GPQA (0-shot)      | 3.69|
+|MuSR (0-shot)      | 5.50|
+|MMLU-PRO (5-shot)  |23.57|
+