Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
 datasets:
 - emozilla/yarn-train-tokenized-16k-mistral
 metrics:
 - perplexity
-library_name: transformers
-license: apache-2.0
-language:
-- en
+model-index:
+- name: Yarn-Mistral-7b-64k
+  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: 59.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Yarn-Mistral-7b-64k
+      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: 82.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Yarn-Mistral-7b-64k
+      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: 62.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Yarn-Mistral-7b-64k
+      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: 41.86
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Yarn-Mistral-7b-64k
+      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: 77.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Yarn-Mistral-7b-64k
+      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: 33.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NousResearch/Yarn-Mistral-7b-64k
+      name: Open LLM Leaderboard
 ---
 
 # Model Card: Nous-Yarn-Mistral-7b-64k
@@ -59,4 +162,17 @@ Short context benchmarks showing that quality degradation is minimal:
  - [honglu2875](https://github.com/honglu2875): Paper and evals
 
 The authors would like to thank LAION AI for their support of compute for this model.
-It was trained on the [JUWELS](https://www.fz-juelich.de/en/ias/jsc/systems/supercomputers/juwels) supercomputer.
+It was trained on the [JUWELS](https://www.fz-juelich.de/en/ias/jsc/systems/supercomputers/juwels) supercomputer.
+# [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_NousResearch__Yarn-Mistral-7b-64k)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.63|
+|AI2 Reasoning Challenge (25-Shot)|59.90|
+|HellaSwag (10-Shot)              |82.51|
+|MMLU (5-Shot)                    |62.96|
+|TruthfulQA (0-shot)              |41.86|
+|Winogrande (5-shot)              |77.27|
+|GSM8k (5-shot)                   |33.28|
+