Adding Evaluation Results (#1)

- Adding Evaluation Results (1f9a697e0ce879e1c53b26245c7c4bd3c21441e6)

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- KingNish/Reasoning-Llama-1b-v0.1
-- zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO
-- prithivMLmods/Bellatrix-Tiny-1B-R1
+license: llama3.2
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.2
+base_model:
+- KingNish/Reasoning-Llama-1b-v0.1
+- zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO
+- prithivMLmods/Bellatrix-Tiny-1B-R1
+model-index:
+- name: Llama_3.2_1b_OpenTree_R1_0.1
+  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: 53.66
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
+      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: 6.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
+      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: 4.76
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
+      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: 0.34
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
+      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: 1.6
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
+      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: 7.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -40,4 +135,17 @@ models:
 base_model: zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO
 dtype: bfloat16
 normalize: true
-```
+```
+# [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_OpenTree_R1_0.1-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |12.34|
+|IFEval (0-Shot)    |53.66|
+|BBH (3-Shot)       | 6.21|
+|MATH Lvl 5 (4-Shot)| 4.76|
+|GPQA (0-shot)      | 0.34|
+|MuSR (0-shot)      | 1.60|
+|MMLU-PRO (5-shot)  | 7.50|
+