Adding Evaluation Results

README.md

@@ -1,14 +1,109 @@
 ---
-base_model:
-- cognitivecomputations/Dolphin3.0-Llama3.2-3B
-- bunnycore/Llama-3.2-3B-R1-lora
+language:
+- en
+license: llama3.2
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.2
-language:
-- en
+base_model:
+- cognitivecomputations/Dolphin3.0-Llama3.2-3B
+- bunnycore/Llama-3.2-3B-R1-lora
+model-index:
+- name: Porpoise-R1-Llama3.2-3b
+  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: 43.52
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Porpoise-R1-Llama3.2-3b
+      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: 12.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Porpoise-R1-Llama3.2-3b
+      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: 4.23
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Porpoise-R1-Llama3.2-3b
+      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: 2.24
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Porpoise-R1-Llama3.2-3b
+      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: 6.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Porpoise-R1-Llama3.2-3b
+      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: 12.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Porpoise-R1-Llama3.2-3b
+      name: Open LLM Leaderboard
 ---
 # Merge
 
@@ -39,4 +134,17 @@ models:
   - model: cognitivecomputations/Dolphin3.0-Llama3.2-3B+bunnycore/Llama-3.2-3B-R1-lora
 tokenizer_source: cognitivecomputations/Dolphin3.0-Llama3.2-3B
 
-```
+```
+# [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/Triangle104__Porpoise-R1-Llama3.2-3b-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.63|
+|IFEval (0-Shot)    |43.52|
+|BBH (3-Shot)       |12.93|
+|MATH Lvl 5 (4-Shot)| 4.23|
+|GPQA (0-shot)      | 2.24|
+|MuSR (0-shot)      | 6.44|
+|MMLU-PRO (5-shot)  |12.41|
+