Adding Evaluation Results (#1)

- Adding Evaluation Results (95c6869417222105d27f10584973f6070ace7936)

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- elinas/Chronos-Gold-12B-1.0
-- ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
-- nbeerbower/Mistral-Nemo-Prism-12B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- elinas/Chronos-Gold-12B-1.0
+- ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
+- nbeerbower/Mistral-Nemo-Prism-12B
+model-index:
+- name: Chronos-Prism_V1.0
+  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: 32.59
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Chronos-Prism_V1.0
+      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: 36.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Chronos-Prism_V1.0
+      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: 11.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Chronos-Prism_V1.0
+      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: 7.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Chronos-Prism_V1.0
+      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: 14.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Chronos-Prism_V1.0
+      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: 29.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Chronos-Prism_V1.0
+      name: Open LLM Leaderboard
 ---
 Model details:
 -
@@ -57,3 +151,17 @@ parameters:
   int8_mask: true
 dtype: float16
 ```
+
+# [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__Chronos-Prism_V1.0-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.12|
+|IFEval (0-Shot)    |32.59|
+|BBH (3-Shot)       |36.58|
+|MATH Lvl 5 (4-Shot)|11.63|
+|GPQA (0-shot)      | 7.94|
+|MuSR (0-shot)      |14.28|
+|MMLU-PRO (5-shot)  |29.70|
+