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

@@ -1,12 +1,107 @@
 ---
-base_model:
-- NotASI/FineTome-Llama3.2-1B-0929
-- unsloth/Llama-3.2-1B-Instruct
+license: llama3.2
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.2
+base_model:
+- NotASI/FineTome-Llama3.2-1B-0929
+- unsloth/Llama-3.2-1B-Instruct
+model-index:
+- name: FineTome-v1.5-Llama3.2-1B-1007
+  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: 39.24
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-1B-1007
+      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: 5.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-1B-1007
+      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: 1.36
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-1B-1007
+      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=NotASI/FineTome-v1.5-Llama3.2-1B-1007
+      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: 2.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-1B-1007
+      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: 4.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-1B-1007
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -40,4 +135,17 @@ parameters:
   normalize: true
   int8_mask: true
 dtype: bfloat16
-```
+```
+# [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_NotASI__FineTome-v1.5-Llama3.2-1B-1007)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 8.94|
+|IFEval (0-Shot)    |39.24|
+|BBH (3-Shot)       | 5.80|
+|MATH Lvl 5 (4-Shot)| 1.36|
+|GPQA (0-shot)      | 0.00|
+|MuSR (0-shot)      | 2.50|
+|MMLU-PRO (5-shot)  | 4.74|
+