Adding Evaluation Results

README.md

@@ -1,9 +1,11 @@
 ---
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
 base_model:
 - arcee-ai/Virtuoso-Small
 - CultriX/SeQwence-14B-EvolMerge
@@ -12,11 +14,104 @@ base_model:
 - underwoods/medius-erebus-magnum-14b
 - sometimesanotion/lamarck-14b-prose-model_stock
 - sometimesanotion/lamarck-14b-reason-model_stock
-language:
-- en
 metrics:
 - accuracy
 pipeline_tag: text-generation
+model-index:
+- name: Lamarck-14B-v0.3
+  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: 50.32
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sometimesanotion/Lamarck-14B-v0.3
+      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: 51.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sometimesanotion/Lamarck-14B-v0.3
+      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: 32.4
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sometimesanotion/Lamarck-14B-v0.3
+      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: 18.46
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sometimesanotion/Lamarck-14B-v0.3
+      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: 18.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sometimesanotion/Lamarck-14B-v0.3
+      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: 49.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sometimesanotion/Lamarck-14B-v0.3
+      name: Open LLM Leaderboard
 ---
 ![Lamarck.webp](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.3/resolve/main/Lamarck.webp)
 ---
@@ -227,4 +322,17 @@ dtype:               bfloat16
 out_dtype:           bfloat16
 ---
 
-```
+```
+# [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_sometimesanotion__Lamarck-14B-v0.3)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.58|
+|IFEval (0-Shot)    |50.32|
+|BBH (3-Shot)       |51.27|
+|MATH Lvl 5 (4-Shot)|32.40|
+|GPQA (0-shot)      |18.46|
+|MuSR (0-shot)      |18.00|
+|MMLU-PRO (5-shot)  |49.01|
+