Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,21 +1,116 @@
 ---
-library_name: transformers
+language:
+- en
 license: llama3.2
-base_model: macadeliccc/magistrate-3.2-3b-base
-datasets:
-- teknium/OpenHermes-2.5
-- NousResearch/hermes-function-calling-v1
-- arcee-ai/The-Tome
-- cognitivecomputations/SystemChat-2.0
+library_name: transformers
 tags:
 - spectrum
 - llama-3
 - axolotl
 - legal
 - HFforLegal
-language:
-- en
+base_model: macadeliccc/magistrate-3.2-3b-base
+datasets:
+- teknium/OpenHermes-2.5
+- NousResearch/hermes-function-calling-v1
+- arcee-ai/The-Tome
+- cognitivecomputations/SystemChat-2.0
 pipeline_tag: text-generation
+model-index:
+- name: magistrate-3.2-3b-it
+  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: 22.92
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=macadeliccc/magistrate-3.2-3b-it
+      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: 5.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=macadeliccc/magistrate-3.2-3b-it
+      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: 1.59
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=macadeliccc/magistrate-3.2-3b-it
+      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: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=macadeliccc/magistrate-3.2-3b-it
+      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: 5.74
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=macadeliccc/magistrate-3.2-3b-it
+      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: 6.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=macadeliccc/magistrate-3.2-3b-it
+      name: Open LLM Leaderboard
 ---
 # magistrate-3.2-3b-it
 
@@ -759,4 +854,17 @@ The following hyperparameters were used during training:
 - Transformers 4.45.0
 - Pytorch 2.3.1+cu121
 - Datasets 2.21.0
-- Tokenizers 0.20.0
+- Tokenizers 0.20.0
+# [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_macadeliccc__magistrate-3.2-3b-it)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 7.03|
+|IFEval (0-Shot)    |22.92|
+|BBH (3-Shot)       | 5.32|
+|MATH Lvl 5 (4-Shot)| 1.59|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 5.74|
+|MMLU-PRO (5-shot)  | 6.58|
+