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

@@ -2,6 +2,109 @@
 license: mit
 datasets:
 - DAMO-NLP-SG/LongCorpus-2.5B
+model-index:
+- name: CLEX-Mixtral-8x7B-Chat-32K
+  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: 66.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DAMO-NLP-SG/CLEX-Mixtral-8x7B-Chat-32K
+      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: 86.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DAMO-NLP-SG/CLEX-Mixtral-8x7B-Chat-32K
+      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: 70.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DAMO-NLP-SG/CLEX-Mixtral-8x7B-Chat-32K
+      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: 56.47
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DAMO-NLP-SG/CLEX-Mixtral-8x7B-Chat-32K
+      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: 82.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DAMO-NLP-SG/CLEX-Mixtral-8x7B-Chat-32K
+      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: 50.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DAMO-NLP-SG/CLEX-Mixtral-8x7B-Chat-32K
+      name: Open LLM Leaderboard
 ---
 
 # CLEX: Continuous Length Extrapolation for Large Language Models
@@ -80,4 +183,17 @@ If you find our project useful, hope you can star our repo and cite our paper as
   journal = {arXiv preprint arXiv:2310.16450},
   url = {https://arxiv.org/abs/2310.16450}
 }
-```
+```
+# [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_DAMO-NLP-SG__CLEX-Mixtral-8x7B-Chat-32K)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.75|
+|AI2 Reasoning Challenge (25-Shot)|66.38|
+|HellaSwag (10-Shot)              |86.48|
+|MMLU (5-Shot)                    |70.12|
+|TruthfulQA (0-shot)              |56.47|
+|Winogrande (5-shot)              |82.56|
+|GSM8k (5-shot)                   |50.49|
+