Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- Nitral-AI/Mika-Longtext-7b
-- ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b
+license: other
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: other
+base_model:
+- Nitral-AI/Mika-Longtext-7b
+- ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b
+model-index:
+- name: Mika-Lelantacles-7b-Longtext
+  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: 67.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Mika-Lelantacles-7b-Longtext
+      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: 86.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Mika-Lelantacles-7b-Longtext
+      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: 63.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Mika-Lelantacles-7b-Longtext
+      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: 70.15
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Mika-Lelantacles-7b-Longtext
+      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: 79.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Mika-Lelantacles-7b-Longtext
+      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: 57.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Nitral-AI/Mika-Lelantacles-7b-Longtext
+      name: Open LLM Leaderboard
 ---
 
 
@@ -39,4 +142,17 @@ parameters:
       value: [1, 0.5, 0.7, 0.3, 0]
     - value: 0.5
 dtype: bfloat16
-```
+```
+# [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_Nitral-AI__Mika-Lelantacles-7b-Longtext)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.86|
+|AI2 Reasoning Challenge (25-Shot)|67.66|
+|HellaSwag (10-Shot)              |86.34|
+|MMLU (5-Shot)                    |63.29|
+|TruthfulQA (0-shot)              |70.15|
+|Winogrande (5-shot)              |79.79|
+|GSM8k (5-shot)                   |57.92|
+