Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model: mistralai/Mistral-Nemo-Base-2407
 license: cc-by-nc-4.0
+library_name: transformers
 tags:
 - general-purpose
 - roleplay
 - storywriting
 - merge
 - finetune
-library_name: transformers
+base_model: mistralai/Mistral-Nemo-Base-2407
+model-index:
+- name: Chronos-Gold-12B-1.0
+  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: 31.66
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=elinas/Chronos-Gold-12B-1.0
+      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: 35.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=elinas/Chronos-Gold-12B-1.0
+      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: 4.38
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=elinas/Chronos-Gold-12B-1.0
+      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: 9.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=elinas/Chronos-Gold-12B-1.0
+      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: 19.42
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=elinas/Chronos-Gold-12B-1.0
+      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: 27.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=elinas/Chronos-Gold-12B-1.0
+      name: Open LLM Leaderboard
 ---
 
 # Chronos Gold 12B-1.0
@@ -78,4 +173,17 @@ This is one of multiple models to come out in the series by size and model archi
 
 Please be mindful of the license. This is strictly non-commercial, but free to use at your own leisure personally. Outputs generated by the model are not reflective of my views.
 
-Contact me on Discord for inquiries.
+Contact me on Discord for inquiries.
+# [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_elinas__Chronos-Gold-12B-1.0)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.40|
+|IFEval (0-Shot)    |31.66|
+|BBH (3-Shot)       |35.91|
+|MATH Lvl 5 (4-Shot)| 4.38|
+|GPQA (0-shot)      | 9.06|
+|MuSR (0-shot)      |19.42|
+|MMLU-PRO (5-shot)  |27.98|
+