Adding Evaluation Results (#1)

- Adding Evaluation Results (b61798721d27530b1f704445fdc67fe812f61c23)

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
 language:
 - en
 license: apache-2.0
@@ -13,8 +12,104 @@ tags:
 - logic
 - math
 - python
+base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
 datasets:
 - theprint/CleverBoi-Data-20k
+model-index:
+- name: CleverBoi-Nemo-12B-v2
+  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: 20.46
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      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: 31.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      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: 8.61
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      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: 8.5
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      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: 11.43
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      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: 24.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/CleverBoi-Nemo-12B-v2
+      name: Open LLM Leaderboard
 ---
 <img src="https://huggingface.co/theprint/CleverBoi-Gemma-2-9B/resolve/main/cleverboi.png"/>
 
@@ -33,4 +128,17 @@ This model has been fine tuned for 1 epoch on the CleverBoi-Data-20k data set.
 
 This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+# [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_theprint__CleverBoi-Nemo-12B-v2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.57|
+|IFEval (0-Shot)    |20.46|
+|BBH (3-Shot)       |31.65|
+|MATH Lvl 5 (4-Shot)| 8.61|
+|GPQA (0-shot)      | 8.50|
+|MuSR (0-shot)      |11.43|
+|MMLU-PRO (5-shot)  |24.76|
+