Adding Evaluation Results

#4
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -233,3 +233,17 @@ This is the **Full-Weight** of WizardLM-13B V1.1 model.
233
  - πŸ”₯πŸ”₯πŸ”₯ [7/7/2023] The **WizardLM-13B-V1.1** achieves **6.74** on [MT-Bench Leaderboard](https://chat.lmsys.org/?leaderboard), **86.32%** on [AlpacaEval Leaderboard](https://tatsu-lab.github.io/alpaca_eval/), and **99.3%** on [WizardLM Eval](https://github.com/nlpxucan/WizardLM/blob/main/WizardLM/data/WizardLM_testset.jsonl). (Note: MT-Bench and AlpacaEval are all self-test, will push update and request review. All tests are completed under their official settings.)
234
 
235
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  - πŸ”₯πŸ”₯πŸ”₯ [7/7/2023] The **WizardLM-13B-V1.1** achieves **6.74** on [MT-Bench Leaderboard](https://chat.lmsys.org/?leaderboard), **86.32%** on [AlpacaEval Leaderboard](https://tatsu-lab.github.io/alpaca_eval/), and **99.3%** on [WizardLM Eval](https://github.com/nlpxucan/WizardLM/blob/main/WizardLM/data/WizardLM_testset.jsonl). (Note: MT-Bench and AlpacaEval are all self-test, will push update and request review. All tests are completed under their official settings.)
234
 
235
 
236
+
237
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
238
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__WizardLM-13B-V1-1-SuperHOT-8K-GPTQ)
239
+
240
+ | Metric | Value |
241
+ |-----------------------|---------------------------|
242
+ | Avg. | 48.79 |
243
+ | ARC (25-shot) | 57.0 |
244
+ | HellaSwag (10-shot) | 80.32 |
245
+ | MMLU (5-shot) | 47.08 |
246
+ | TruthfulQA (0-shot) | 53.46 |
247
+ | Winogrande (5-shot) | 74.35 |
248
+ | GSM8K (5-shot) | 0.68 |
249
+ | DROP (3-shot) | 28.62 |