Adding Evaluation Results (#1)

- Adding Evaluation Results (92a8aa76399706da4761fdd6d30ee458d1521459)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,11 +1,106 @@
 ---
-base_model:
-- meta-llama/Meta-Llama-3.1-8B
+license: mit
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: mit
+base_model:
+- meta-llama/Meta-Llama-3.1-8B
+model-index:
+- name: Llama-3.1-8B-Base-Instruct-SLERP
+  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: 29.07
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP
+      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: 29.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP
+      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: 10.5
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP
+      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: 6.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP
+      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: 9.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP
+      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: 29.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -57,4 +152,17 @@ parameters:
     - 0
   - value: 0.5
 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_vhab10__Llama-3.1-8B-Base-Instruct-SLERP)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.02|
+|IFEval (0-Shot)    |29.07|
+|BBH (3-Shot)       |29.93|
+|MATH Lvl 5 (4-Shot)|10.50|
+|GPQA (0-shot)      | 6.15|
+|MuSR (0-shot)      | 9.37|
+|MMLU-PRO (5-shot)  |29.12|
+