Adding Evaluation Results (#1)

- Adding Evaluation Results (4256a968fea719a6cd365279812a8b1b01a2846b)


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

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- djuna-test-lab/TEST-L3.2-3B-ReWish-8B
-- unsloth/Llama-3.2-3B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- djuna-test-lab/TEST-L3.2-3B-ReWish-8B
+- unsloth/Llama-3.2-3B
+model-index:
+- name: TEST-L3.2-ReWish-3B-ties-w-base
+  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: 63.53
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B-ties-w-base
+      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: 22.07
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B-ties-w-base
+      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: 12.92
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B-ties-w-base
+      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: 4.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B-ties-w-base
+      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: 7.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B-ties-w-base
+      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: 23.62
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna-test-lab/TEST-L3.2-ReWish-3B-ties-w-base
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,3 +138,17 @@ parameters:
   int8_mask: true
 dtype: float32
 ```
+
+# [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_djuna-test-lab__TEST-L3.2-ReWish-3B-ties-w-base)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.42|
+|IFEval (0-Shot)    |63.53|
+|BBH (3-Shot)       |22.07|
+|MATH Lvl 5 (4-Shot)|12.92|
+|GPQA (0-shot)      | 4.47|
+|MuSR (0-shot)      | 7.92|
+|MMLU-PRO (5-shot)  |23.62|
+