Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-library_name: transformers
+language:
+- en
 license: cc-by-sa-4.0
+library_name: transformers
 datasets:
 - mlabonne/chatml_dpo_pairs
 - ResplendentAI/Synthetic_Soul_1k
-language:
-- en
+model-index:
+- name: Flora_DPO_7B
+  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: 71.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
+      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: 88.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
+      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: 64.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
+      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: 71.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
+      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: 84.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
+      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: 65.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
+      name: Open LLM Leaderboard
 ---
 
 # Flora DPO
@@ -18,4 +121,17 @@ Quants available here:
 
 https://huggingface.co/solidrust/Flora-7B-DPO-AWQ
 
-https://huggingface.co/Test157t/ResplendentAI-Flora_DPO_7B-5bpw-exl2
+https://huggingface.co/Test157t/ResplendentAI-Flora_DPO_7B-5bpw-exl2
+# [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_ResplendentAI__Flora_DPO_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.26|
+|AI2 Reasoning Challenge (25-Shot)|71.76|
+|HellaSwag (10-Shot)              |88.28|
+|MMLU (5-Shot)                    |64.13|
+|TruthfulQA (0-shot)              |71.08|
+|Winogrande (5-shot)              |84.53|
+|GSM8k (5-shot)                   |65.81|
+