Adding Evaluation Results (#2)

- Adding Evaluation Results (335ba8faeb0222299d79fe4c15151291852dd002)

README.md

@@ -1,15 +1,109 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - arcee-ai/SuperNova-Medius
 - huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
 - allura-org/TQ2.5-14B-Aletheia-v1
 - EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
 - v000000/Qwen2.5-Lumen-14B
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Q2.5-Veltha-14B-0.5
+  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: 77.96
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 50.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 33.84
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 15.77
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 14.17
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 47.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -65,3 +159,17 @@ models:
       density: 0.45
 
 ```
+
+# [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/djuna__Q2.5-Veltha-14B-0.5-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |39.96|
+|IFEval (0-Shot)    |77.96|
+|BBH (3-Shot)       |50.32|
+|MATH Lvl 5 (4-Shot)|33.84|
+|GPQA (0-shot)      |15.77|
+|MuSR (0-shot)      |14.17|
+|MMLU-PRO (5-shot)  |47.72|
+