Adding Evaluation Results (#2)

- Adding Evaluation Results (9293269c3693659b14a34522c4affbe5783e7e19)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,16 +1,119 @@
 ---
-library_name: trl
-license: apache-2.0
-base_model: teknium/OpenHermes-2.5-Mistral-7B
-datasets:
-- argilla/dpo-mix-7k
 language:
 - en
+license: apache-2.0
+library_name: trl
 tags:
 - distilabel
 - dpo
 - rlaif
 - rlhf
+datasets:
+- argilla/dpo-mix-7k
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: CapybaraHermes-2.5-Mistral-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: 65.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-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: 85.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-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: 63.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-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: 56.91
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-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: 78.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-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: 59.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=argilla/CapybaraHermes-2.5-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 
 # CapybaraHermes-2.5-Mistral-7B
@@ -63,3 +166,17 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **License:** Same as OpenHermes
 - **Finetuned from model [optional]:** [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
 
+
+# [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_argilla__CapybaraHermes-2.5-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.14|
+|AI2 Reasoning Challenge (25-Shot)|65.78|
+|HellaSwag (10-Shot)              |85.45|
+|MMLU (5-Shot)                    |63.13|
+|TruthfulQA (0-shot)              |56.91|
+|Winogrande (5-shot)              |78.30|
+|GSM8k (5-shot)                   |59.29|
+