Adding Evaluation Results (#3)

- Adding Evaluation Results (cea24e58b3fc6a211b230935f3558a5d314e0055)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,12 +1,12 @@
 ---
-license: apache-2.0
-datasets:
-- Intel/orca_dpo_pairs
-- Locutusque/Hercules-v3.0
 language:
 - en
+license: apache-2.0
 tags:
 - conversational
+datasets:
+- Intel/orca_dpo_pairs
+- Locutusque/Hercules-v3.0
 inference:
   parameters:
     do_sample: true
@@ -17,12 +17,115 @@ inference:
     max_new_tokens: 250
     repetition_penalty: 1.1
 widget:
-  - text: Hello who are you?
-    example_title: Identity
-  - text: What can you do?
-    example_title: Capabilities
-  - text: Create a fastapi endpoint to retrieve the weather given a zip code.
-    example_title: Coding
+- text: Hello who are you?
+  example_title: Identity
+- text: What can you do?
+  example_title: Capabilities
+- text: Create a fastapi endpoint to retrieve the weather given a zip code.
+  example_title: Coding
+model-index:
+- name: NeuralReyna-Mini-1.8B-v0.2
+  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: 37.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
+      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: 60.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
+      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: 45.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
+      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: 37.75
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
+      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-v0.2
+      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: 27.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
+      name: Open LLM Leaderboard
 ---
 # NeuralReyna-Mini-1.8B-v0.2
 ![Reyna image](https://th.bing.com/th/id/OIG3.8IBxuT77hh6Y_r1DZ6WK?dpr=2.6&pid=ImgDetMain)
@@ -59,4 +162,17 @@ This model may have overfitted to the DPO training data, and may not perform wel
 
 # 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-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.85|
+|AI2 Reasoning Challenge (25-Shot)|37.80|
+|HellaSwag (10-Shot)              |60.51|
+|MMLU (5-Shot)                    |45.04|
+|TruthfulQA (0-shot)              |37.75|
+|Winogrande (5-shot)              |60.93|
+|GSM8k (5-shot)                   |27.07|
+