Adding Evaluation Results (#2)

- Adding Evaluation Results (b6066983173581c01e99dba2ea2acf41caf2de26)


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

README.md

@@ -2,7 +2,6 @@
 language:
 - en
 license: other
-pipeline_tag: text-generation
 tags:
 - supernova
 - moth
@@ -18,10 +17,106 @@ tags:
 - conversational
 - chat
 - instruct
-model_type: llama
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets:
 - sequelbox/Supernova
+pipeline_tag: text-generation
+model_type: llama
+model-index:
+- name: Llama3.1-8B-MOTH
+  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: 52.08
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
+      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: 26.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
+      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: 11.86
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
+      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: 2.57
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
+      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: 3.79
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
+      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: 25.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-MOTH
+      name: Open LLM Leaderboard
 ---
 
 - MOTH is a general chat AI.
@@ -34,4 +129,17 @@ datasets:
 
 
 
-(uses llama 3.1 license available at https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+(uses llama 3.1 license available at https://huggingface.co/meta-llama/Meta-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-MOTH)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.37|
+|IFEval (0-Shot)    |52.08|
+|BBH (3-Shot)       |26.45|
+|MATH Lvl 5 (4-Shot)|11.86|
+|GPQA (0-shot)      | 2.57|
+|MuSR (0-shot)      | 3.79|
+|MMLU-PRO (5-shot)  |25.48|
+