Adding Evaluation Results (#2)

- Adding Evaluation Results (8b3c6ead3286575b2cd03068071e06112df7a01f)


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

README.md

@@ -1,12 +1,43 @@
 ---
 language:
 - en
-pipeline_tag: text-generation
+license: llama3.1
+library_name: transformers
+tags:
+- mergekit
+- merge
+- shining-valiant
+- shining-valiant-2
+- cobalt
+- plum
+- valiant
+- valiant-labs
+- llama
+- llama-3.1
+- llama-3.1-instruct
+- llama-3.1-instruct-8b
+- llama-3
+- llama-3-instruct
+- llama-3-instruct-8b
+- 8b
+- math
+- math-instruct
+- science
+- physics
+- biology
+- chemistry
+- compsci
+- computer-science
+- engineering
+- technical
+- conversational
+- chat
+- instruct
 base_model:
 - meta-llama/Llama-3.1-8B-Instruct
 - ValiantLabs/Llama3.1-8B-ShiningValiant2
 - ValiantLabs/Llama3.1-8B-Cobalt
-library_name: transformers
+pipeline_tag: text-generation
 model_type: llama
 model-index:
 - name: sequelbox/Llama3.1-8B-PlumMath
@@ -35,38 +66,98 @@ model-index:
     - type: acc
       value: 40.27
       name: acc
-tags:
-- mergekit
-- merge
-- shining-valiant
-- shining-valiant-2
-- cobalt
-- plum
-- valiant
-- valiant-labs
-- llama
-- llama-3.1
-- llama-3.1-instruct
-- llama-3.1-instruct-8b
-- llama-3
-- llama-3-instruct
-- llama-3-instruct-8b
-- 8b
-- math
-- math-instruct
-- science
-- physics
-- biology
-- chemistry
-- compsci
-- computer-science
-- engineering
-- technical
-- conversational
-- chat
-- instruct
-license: llama3.1
-
+  - 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: 22.42
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath
+      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: 16.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath
+      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: 3.93
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath
+      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: 9.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath
+      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: 8.98
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath
+      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: 21.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumMath
+      name: Open LLM Leaderboard
 ---
 # PlumMath
 
@@ -103,3 +194,17 @@ models:
       weight: 0.2
 base_model: 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_sequelbox__Llama3.1-8B-PlumMath)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.80|
+|IFEval (0-Shot)    |22.42|
+|BBH (3-Shot)       |16.45|
+|MATH Lvl 5 (4-Shot)| 3.93|
+|GPQA (0-shot)      | 9.06|
+|MuSR (0-shot)      | 8.98|
+|MMLU-PRO (5-shot)  |21.95|
+