Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
 license: apache-2.0
-base_model: NeuralNovel/Gecko-7B-v0.1
 library_name: transformers
-inference: false
 datasets:
 - Intel/orca_dpo_pairs
+base_model: NeuralNovel/Gecko-7B-v0.1
+inference: false
+model-index:
+- name: Gecko-7B-v0.1-DPO
+  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: 56.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Gecko-7B-v0.1-DPO
+      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: 82.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Gecko-7B-v0.1-DPO
+      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: 60.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Gecko-7B-v0.1-DPO
+      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: 57.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Gecko-7B-v0.1-DPO
+      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: 77.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Gecko-7B-v0.1-DPO
+      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: 45.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Gecko-7B-v0.1-DPO
+      name: Open LLM Leaderboard
 ---
 
 ![Gecko](https://i.ibb.co/gtf92Nt/OIG-43.jpg)
@@ -44,4 +147,17 @@ The user is responsible for their output and must use this model responsibly.
 
 Trained on a single 80GB A100 for 2 hours trained using Axolotl
 
-Thank you to **h2m** for the generous funding. 
+Thank you to **h2m** for the generous funding. 
+# [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__Gecko-7B-v0.1-DPO)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.22|
+|AI2 Reasoning Challenge (25-Shot)|56.74|
+|HellaSwag (10-Shot)              |82.38|
+|MMLU (5-Shot)                    |60.42|
+|TruthfulQA (0-shot)              |57.42|
+|Winogrande (5-shot)              |77.35|
+|GSM8k (5-shot)                   |45.03|
+