Adding Evaluation Results

README.md

@@ -1,13 +1,107 @@
 ---
-base_model:
-- CultriX/SeQwence-14Bv2
-- CultriX/Qwestion-14B
-- CultriX/SeQwence-14Bv1
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- CultriX/SeQwence-14Bv2
+- CultriX/Qwestion-14B
+- CultriX/SeQwence-14Bv1
+model-index:
+- name: SeQwence-14Bv3
+  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: 57.19
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/SeQwence-14Bv3
+      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: 46.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/SeQwence-14Bv3
+      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: 22.13
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/SeQwence-14Bv3
+      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: 15.32
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/SeQwence-14Bv3
+      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: 17.27
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/SeQwence-14Bv3
+      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: 48.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/SeQwence-14Bv3
+      name: Open LLM Leaderboard
 ---
 # final_model
 
@@ -133,3 +227,17 @@ slices:
       density: 1.0
       weight: 0.33759567132306584
 ```
+
+# [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_CultriX__SeQwence-14Bv3)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |34.41|
+|IFEval (0-Shot)    |57.19|
+|BBH (3-Shot)       |46.39|
+|MATH Lvl 5 (4-Shot)|22.13|
+|GPQA (0-shot)      |15.32|
+|MuSR (0-shot)      |17.27|
+|MMLU-PRO (5-shot)  |48.17|
+