Adding Evaluation Results

README.md

@@ -1,14 +1,4 @@
 ---
-base_model:
-- Qwen/Qwen2.5-72B-Instruct
-- Qwen/Qwen2.5-72B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: other
-license_name: qwen
-inference: true
 language:
 - en
 - ko
@@ -21,6 +11,111 @@ language:
 - it
 - ro
 - zh
+license: other
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- Qwen/Qwen2.5-72B-Instruct
+- Qwen/Qwen2.5-72B
+license_name: qwen
+inference: true
+model-index:
+- name: ultiima-72B
+  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: 71.4
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sakalti/ultiima-72B
+      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: 61.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sakalti/ultiima-72B
+      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: 52.42
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sakalti/ultiima-72B
+      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: 21.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sakalti/ultiima-72B
+      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: 18.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sakalti/ultiima-72B
+      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: 54.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sakalti/ultiima-72B
+      name: Open LLM Leaderboard
 ---
 Built With Qwen
 # merge
@@ -55,4 +150,17 @@ parameters:
   normalize: true
   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/Sakalti__ultiima-72B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |46.58|
+|IFEval (0-Shot)    |71.40|
+|BBH (3-Shot)       |61.10|
+|MATH Lvl 5 (4-Shot)|52.42|
+|GPQA (0-shot)      |21.92|
+|MuSR (0-shot)      |18.12|
+|MMLU-PRO (5-shot)  |54.51|
+