Adding Evaluation Results (#1)

- Adding Evaluation Results (18013ecba18c67ab46158a15d55569fa9ac509fd)

README.md

@@ -1,14 +1,117 @@
 ---
-base_model:
-- ABX-AI/Cerebral-Infinity-7B
-- ABX-AI/Starfinite-Laymospice-v2-7B
+license: other
 library_name: transformers
 tags:
 - mergekit
 - merge
 - mistral
 - not-for-all-audiences
-license: other
+base_model:
+- ABX-AI/Cerebral-Infinity-7B
+- ABX-AI/Starfinite-Laymospice-v2-7B
+model-index:
+- name: Quantum-Citrus-9B
+ 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: 65.19
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ABX-AI/Quantum-Citrus-9B
+ 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: 84.75
+ name: normalized accuracy
+ source:
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ABX-AI/Quantum-Citrus-9B
+ 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: 64.58
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ABX-AI/Quantum-Citrus-9B
+ 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: 55.96
+ source:
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ABX-AI/Quantum-Citrus-9B
+ 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: 79.4
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ABX-AI/Quantum-Citrus-9B
+ 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: 50.57
+ name: accuracy
+ source:
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ABX-AI/Quantum-Citrus-9B
+ name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d936ad52eca001fdcd3245/J0snW3yfLadLuMYERL6X5.png)
@@ -54,4 +157,17 @@ slices:
 merge_method: passthrough
 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_ABX-AI__Quantum-Citrus-9B)
+
+| Metric |Value|
+|---------------------------------|----:|
+|Avg. |66.74|
+|AI2 Reasoning Challenge (25-Shot)|65.19|
+|HellaSwag (10-Shot) |84.75|
+|MMLU (5-Shot) |64.58|
+|TruthfulQA (0-shot) |55.96|
+|Winogrande (5-shot) |79.40|
+|GSM8k (5-shot) |50.57|
+