Adding Evaluation Results

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: mlabonne/NeuralMarcoro14-7B
 license: cc-by-nc-4.0
 tags:
 - mlabonne/NeuralMarcoro14-7B
@@ -10,6 +9,110 @@ tags:
 - mistral
 datasets:
 - hromi/winograd_dpo_basic
+base_model: mlabonne/NeuralMarcoro14-7B
+model-index:
+- name: Turdus
+  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: 73.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Turdus
+      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: 88.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Turdus
+      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: 64.52
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Turdus
+      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: 67.11
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Turdus
+      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: 86.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Turdus
+      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: 67.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Turdus
+      name: Open LLM Leaderboard
 ---
 
 ![](https://wizzion.com/solarpunk_turdus.webp)
@@ -44,4 +147,17 @@ Should this model - or quasi-methodology which lead to it - be of certain pratic
 	doi          = { 10.57967/hf/1611 },
 	publisher    = { Hugging Face }
 }
-```
+```
+# [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_udkai__Turdus)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.66|
+|AI2 Reasoning Challenge (25-Shot)|73.38|
+|HellaSwag (10-Shot)              |88.56|
+|MMLU (5-Shot)                    |64.52|
+|TruthfulQA (0-shot)              |67.11|
+|Winogrande (5-shot)              |86.66|
+|GSM8k (5-shot)                   |67.70|
+