Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- meta-llama/Llama-3.2-3B
-- meta-llama/Llama-3.2-3B-Instruct
-- PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
+license: llama3.2
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.2
+base_model:
+- meta-llama/Llama-3.2-3B
+- meta-llama/Llama-3.2-3B-Instruct
+- PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
+model-index:
+- name: LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+  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: 50.41
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+      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: 22.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+      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: 10.73
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+      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: 4.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+      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: 4.68
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+      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: 23.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
+      name: Open LLM Leaderboard
 ---
 # LLaMa-3.2-Instruct-JankMixBread-v0.1-3B
 
@@ -47,4 +142,17 @@ models:
       density: 0.9
       gamma: 0.01
 
-```
+```
+# [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_PJMixers-Dev__LLaMa-3.2-Instruct-JankMixBread-v0.1-3B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.35|
+|IFEval (0-Shot)    |50.41|
+|BBH (3-Shot)       |22.76|
+|MATH Lvl 5 (4-Shot)|10.73|
+|GPQA (0-shot)      | 4.36|
+|MuSR (0-shot)      | 4.68|
+|MMLU-PRO (5-shot)  |23.15|
+