Adding Evaluation Results

README.md

@@ -1,8 +1,8 @@
 ---
-base_model:
-- cstr/llama3.1-8b-spaetzle-v85
-- cstr/llama3.1-8b-spaetzle-v86
-- cstr/llama3.1-8b-spaetzle-v74
+language:
+- en
+- de
+license: llama3
 tags:
 - merge
 - mergekit
@@ -10,10 +10,105 @@ tags:
 - cstr/llama3.1-8b-spaetzle-v85
 - cstr/llama3.1-8b-spaetzle-v86
 - cstr/llama3.1-8b-spaetzle-v74
-license: llama3
-language:
-- en
-- de
+base_model:
+- cstr/llama3.1-8b-spaetzle-v85
+- cstr/llama3.1-8b-spaetzle-v86
+- cstr/llama3.1-8b-spaetzle-v74
+model-index:
+- name: llama3.1-8b-spaetzle-v90
+  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: 73.56
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cstr/llama3.1-8b-spaetzle-v90
+      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: 32.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cstr/llama3.1-8b-spaetzle-v90
+      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: 13.37
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cstr/llama3.1-8b-spaetzle-v90
+      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: 4.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cstr/llama3.1-8b-spaetzle-v90
+      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: 11.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cstr/llama3.1-8b-spaetzle-v90
+      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: 30.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cstr/llama3.1-8b-spaetzle-v90
+      name: Open LLM Leaderboard
 ---
 
 # llama3.1-8b-spaetzle-v90
@@ -91,3 +186,17 @@ dtype: float16
 
 Use with llama3 chat template as common. Here are GGUF quants for use with llama.cpp & wrappers as e.g. ollama: [cstr/llama3.1-8b-spaetzle-v90-GGUF](https://huggingface.co/cstr/llama3.1-8b-spaetzle-v90-GGUF)
 
+
+# [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_cstr__llama3.1-8b-spaetzle-v90)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.59|
+|IFEval (0-Shot)    |73.56|
+|BBH (3-Shot)       |32.76|
+|MATH Lvl 5 (4-Shot)|13.37|
+|GPQA (0-shot)      | 4.36|
+|MuSR (0-shot)      |11.15|
+|MMLU-PRO (5-shot)  |30.34|
+