Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-base_model:
-- InferenceIllusionist/Excalibur-7b
+license: apache-2.0
 library_name: transformers
 tags:
 - finetune
 - dpo
 - chatml
-license: apache-2.0
+base_model:
+- InferenceIllusionist/Excalibur-7b
 datasets:
 - Intel/orca_dpo_pairs
+model-index:
+- name: Excalibur-7b-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: 70.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Excalibur-7b-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: 87.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Excalibur-7b-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: 65.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Excalibur-7b-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: 70.82
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Excalibur-7b-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: 82.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Excalibur-7b-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: 65.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Excalibur-7b-DPO
+      name: Open LLM Leaderboard
 ---
 
 
@@ -39,4 +142,17 @@ Select the gguf file of your choice in [Koboldcpp](https://github.com/LostRuins/
 <img src="https://i.imgur.com/x8vqH29.png" width="425"/>
 
 ## Prompt Format
-* For best results please use ChatML for the prompt format. Alpaca may also work.
+* For best results please use ChatML for the prompt format. Alpaca may also work.
+# [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_InferenceIllusionist__Excalibur-7b-DPO)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.84|
+|AI2 Reasoning Challenge (25-Shot)|70.90|
+|HellaSwag (10-Shot)              |87.93|
+|MMLU (5-Shot)                    |65.46|
+|TruthfulQA (0-shot)              |70.82|
+|Winogrande (5-shot)              |82.48|
+|GSM8k (5-shot)                   |65.43|
+