Adding Evaluation Results (#1)

- Adding Evaluation Results (86570922b6686d309bfd6ff216049465356c423b)

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- hyunseoki/llama3.2-1b-Open-R1-GRPO-test0
-- artificialguybr/LLAMA-3.2-1B-OpenHermes2.5
-- artificialguybr/LLAMA3.2-1B-Synthia-II-Redmond
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- hyunseoki/llama3.2-1b-Open-R1-GRPO-test0
+- artificialguybr/LLAMA-3.2-1B-OpenHermes2.5
+- artificialguybr/LLAMA3.2-1B-Synthia-II-Redmond
+model-index:
+- name: Llama_3.2_1b_Synopsys_0.11
+  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: 28.42
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_Synopsys_0.11
+      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: 3.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_Synopsys_0.11
+      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: 1.28
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_Synopsys_0.11
+      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: 1.68
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_Synopsys_0.11
+      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: 3.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_Synopsys_0.11
+      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: 1.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_Synopsys_0.11
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,3 +138,17 @@ chat_template: auto
 tokenizer:
   source: union
 ```
+
+# [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/Nexesenex__Llama_3.2_1b_Synopsys_0.11-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 6.56|
+|IFEval (0-Shot)    |28.42|
+|BBH (3-Shot)       | 3.44|
+|MATH Lvl 5 (4-Shot)| 1.28|
+|GPQA (0-shot)      | 1.68|
+|MuSR (0-shot)      | 3.15|
+|MMLU-PRO (5-shot)  | 1.36|
+