Adding Evaluation Results

#6
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -261,4 +261,17 @@ The model and dataset are intended and licensed for research use only. I've use
261
  - the base model is LLaMa, which has it's own special research license
262
  - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
263
 
264
- So, to reiterate: this model (and datasets) cannot be used commercially.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
261
  - the base model is LLaMa, which has it's own special research license
262
  - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
263
 
264
+ So, to reiterate: this model (and datasets) cannot be used commercially.
265
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
266
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-13b)
267
+
268
+ | Metric | Value |
269
+ |-----------------------|---------------------------|
270
+ | Avg. | 48.94 |
271
+ | ARC (25-shot) | 58.28 |
272
+ | HellaSwag (10-shot) | 81.05 |
273
+ | MMLU (5-shot) | 50.03 |
274
+ | TruthfulQA (0-shot) | 51.57 |
275
+ | Winogrande (5-shot) | 76.24 |
276
+ | GSM8K (5-shot) | 6.97 |
277
+ | DROP (3-shot) | 18.42 |