Adding Evaluation Results

README.md

@@ -1,16 +1,111 @@
 ---
-base_model:
-- meta-llama/Llama-3.1-8B-Instruct
-- akjindal53244/Llama-3.1-Storm-8B
-- arcee-ai/Llama-3.1-SuperNova-Lite
-- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+language:
+- en
 library_name: transformers
 tags:
 - mergekit
 - merge
 - llama3.1
-language:
-- en
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+- akjindal53244/Llama-3.1-Storm-8B
+- arcee-ai/Llama-3.1-SuperNova-Lite
+- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+model-index:
+- name: Llama-3.1-8B-Instruct-Zeus
+  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: 79.41
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Llama-3.1-8B-Instruct-Zeus
+      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: 31.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Llama-3.1-8B-Instruct-Zeus
+      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: 19.18
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Llama-3.1-8B-Instruct-Zeus
+      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: 6.82
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Llama-3.1-8B-Instruct-Zeus
+      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: 8.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Llama-3.1-8B-Instruct-Zeus
+      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: 32.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/Llama-3.1-8B-Instruct-Zeus
+      name: Open LLM Leaderboard
 ---
 # ZEUS
 
@@ -58,4 +153,17 @@ slices:
   - layer_range: [0, 32]
     model: meta-llama/Llama-3.1-8B-Instruct
 tokenizer_source: meta-llama/Llama-3.1-8B-Instruct
-```
+```
+# [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_T145__Llama-3.1-8B-Instruct-Zeus)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |29.59|
+|IFEval (0-Shot)    |79.41|
+|BBH (3-Shot)       |31.39|
+|MATH Lvl 5 (4-Shot)|19.18|
+|GPQA (0-shot)      | 6.82|
+|MuSR (0-shot)      | 8.57|
+|MMLU-PRO (5-shot)  |32.14|
+