Adding Evaluation Results

README.md

@@ -1,16 +1,117 @@
 ---
-base_model:
-- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
-- NeuralNovel/Gecko-7B-v0.1-DPO
+license: apache-2.0
 tags:
 - mergekit
 - merge
-license: apache-2.0
-
 datasets:
 - Intel/orca_dpo_pairs
 - NeuralNovel/Neural-Story-v1
-
+base_model:
+- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
+- NeuralNovel/Gecko-7B-v0.1-DPO
+model-index:
+- name: Tiger-7b-v0.1
+  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: 59.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
+      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: 83.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
+      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: 61.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
+      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: 61.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
+      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: 77.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
+      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: 46.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
+      name: Open LLM Leaderboard
 ---
 
 
@@ -70,3 +171,17 @@ 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_NeuralNovel__Tiger-7b-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |65.02|
+|AI2 Reasoning Challenge (25-Shot)|59.98|
+|HellaSwag (10-Shot)              |83.21|
+|MMLU (5-Shot)                    |61.42|
+|TruthfulQA (0-shot)              |61.03|
+|Winogrande (5-shot)              |77.66|
+|GSM8k (5-shot)                   |46.78|
+