Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
-base_model: teknium/OpenHermes-2.5-Mistral-7B
 license: apache-2.0
 datasets:
 - argilla/distilabel-intel-orca-dpo-pairs
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: kellemar-DPO-7B-v1.01
+  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: 65.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decruz07/kellemar-DPO-7B-v1.01
+      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: 85.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decruz07/kellemar-DPO-7B-v1.01
+      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: 63.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decruz07/kellemar-DPO-7B-v1.01
+      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: 55.54
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decruz07/kellemar-DPO-7B-v1.01
+      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: 78.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decruz07/kellemar-DPO-7B-v1.01
+      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: 61.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=decruz07/kellemar-DPO-7B-v1.01
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for decruz07/kellemar-DPO-7B-v1.01
@@ -94,4 +197,17 @@ Trained with Labonne's Google Colab Notebook on Finetuning Mistral 7B with DPO.
 
 ## Model Card Contact
 
-@decruz on X/Twitter
+@decruz on X/Twitter
+# [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_decruz07__kellemar-DPO-7B-v1.01)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.32|
+|AI2 Reasoning Challenge (25-Shot)|65.78|
+|HellaSwag (10-Shot)              |85.04|
+|MMLU (5-Shot)                    |63.24|
+|TruthfulQA (0-shot)              |55.54|
+|Winogrande (5-shot)              |78.69|
+|GSM8k (5-shot)                   |61.64|
+