Adding Evaluation Results

README.md

@@ -1,10 +1,7 @@
 ---
-base_model:
-- mistralai/Mistral-7B-v0.1
-- SanjiWatsuki/Kunoichi-DPO-v2-7B
-- maywell/PiVoT-0.1-Evil-a
-- mlabonne/ArchBeagle-7B
-- LakoMoor/Silicon-Alice-7B
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
@@ -17,9 +14,115 @@ tags:
 - roleplay
 - rp
 - not-for-all-audiences
-license: apache-2.0
-language:
-- en
+base_model:
+- mistralai/Mistral-7B-v0.1
+- SanjiWatsuki/Kunoichi-DPO-v2-7B
+- maywell/PiVoT-0.1-Evil-a
+- mlabonne/ArchBeagle-7B
+- LakoMoor/Silicon-Alice-7B
+model-index:
+- name: Konstanta-Alpha-V2-7B
+  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: 69.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
+      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: 87.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
+      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: 65.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
+      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: 61.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
+      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: 81.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
+      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: 69.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-Alpha-V2-7B
+      name: Open LLM Leaderboard
 ---
 # Konstanta-Alpha-V2-7B 
 
@@ -100,4 +203,17 @@ parameters:
   int8_mask: true
   normalize: true
 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_Inv__Konstanta-Alpha-V2-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.35|
+|AI2 Reasoning Challenge (25-Shot)|69.62|
+|HellaSwag (10-Shot)              |87.14|
+|MMLU (5-Shot)                    |65.11|
+|TruthfulQA (0-shot)              |61.08|
+|Winogrande (5-shot)              |81.22|
+|GSM8k (5-shot)                   |69.90|
+