Adding Evaluation Results

README.md

@@ -1,10 +1,10 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - argilla/OpenHermes2.5-dpo-binarized-alpha
 - Locutusque/Hercules-v3.0
-language:
-- en
 inference:
   parameters:
     do_sample: true
@@ -14,6 +14,109 @@ inference:
     min_new_tokens: 2
     max_new_tokens: 250
     repetition_penalty: 1.1
+model-index:
+- name: NeuralReyna-Mini-1.8B-v0.3
+  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: 35.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
+      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: 61.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
+      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: 44.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
+      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: 41.99
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
+      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: 60.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
+      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: 6.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
+      name: Open LLM Leaderboard
 ---
 # NeuralReyna-Mini-1.8B-v0.3
 ![Reyna image](https://th.bing.com/th/id/OIG3.8IBxuT77hh6Y_r1DZ6WK?dpr=2.6&pid=ImgDetMain)
@@ -28,4 +131,17 @@ Coming soon
 
 # Contributions
 
-Thanks to @aloobun and @Locutusque for their contributions to this model. 
+Thanks to @aloobun and @Locutusque for their contributions to this model. 
+# [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_M4-ai__NeuralReyna-Mini-1.8B-v0.3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |41.77|
+|AI2 Reasoning Challenge (25-Shot)|35.58|
+|HellaSwag (10-Shot)              |61.13|
+|MMLU (5-Shot)                    |44.22|
+|TruthfulQA (0-shot)              |41.99|
+|Winogrande (5-shot)              |60.93|
+|GSM8k (5-shot)                   | 6.75|
+