Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,6 +1,5 @@
 ---
 license: apache-2.0
-base_model: mistralai/mistral-7b-v0.1
 datasets:
 - ai2_arc
 - allenai/ultrafeedback_binarized_cleaned
@@ -43,6 +42,110 @@ datasets:
 - WhiteRabbitNeo/WRN-Chapter-1
 - WhiteRabbitNeo/WRN-Chapter-2
 - winogrande
+base_model: mistralai/mistral-7b-v0.1
+model-index:
+- name: bagel-dpo-7b-v0.4
+  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: 67.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.4
+      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: 84.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.4
+      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: 61.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.4
+      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: 63.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.4
+      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: 78.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.4
+      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: 46.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jondurbin/bagel-dpo-7b-v0.4
+      name: Open LLM Leaderboard
 ---
 
 # A bagel, with everything
@@ -810,4 +913,17 @@ https://bmc.link/jondurbin
 
 ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
 
-BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
+BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
+# [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_jondurbin__bagel-dpo-7b-v0.4)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.13|
+|AI2 Reasoning Challenge (25-Shot)|67.58|
+|HellaSwag (10-Shot)              |84.30|
+|MMLU (5-Shot)                    |61.95|
+|TruthfulQA (0-shot)              |63.94|
+|Winogrande (5-shot)              |78.14|
+|GSM8k (5-shot)                   |46.85|
+