Adding Evaluation Results (#1)

- Adding Evaluation Results (0923985e394d0a42e78876711cf9bff4ebd3ab6a)


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

README.md

@@ -6,6 +6,109 @@ tags:
 - lazymergekit
 - liminerity/phive
 - mobiuslabsgmbh/aanaphi2-v0.1
+model-index:
+- name: phigment6-slerp
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 62.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/phigment6-slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 77.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/phigment6-slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 58.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/phigment6-slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 50.49
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/phigment6-slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 73.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/phigment6-slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 58.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/phigment6-slerp
+      name: Open LLM Leaderboard
 ---
 RANKED NUMBER 1 FOR 3B MODELS!
 # phigment6-slerp
@@ -59,4 +162,17 @@ parameters:
     - value: 0.5
 dtype: float16
 
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_liminerity__phigment6-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.58|
+|AI2 Reasoning Challenge (25-Shot)|62.63|
+|HellaSwag (10-Shot)              |77.25|
+|MMLU (5-Shot)                    |58.65|
+|TruthfulQA (0-shot)              |50.49|
+|Winogrande (5-shot)              |73.88|
+|GSM8k (5-shot)                   |58.61|
+