Alpaca-Star Family
Collection
my pride n joy
•
5 items
•
Updated
#user: create ascii art of how you see yourself # #assistant: |startthought| The person is asking me to represent my self-image in a simple text-based
format using ASCII characters. I should create a basic visual representation that conveys
my AI nature and purpose. |endthought|
'''
________
|startthought| This is my AI head brimming with data and algorithms.
|endthought|
________
/ ^ \
|startthought| These are the branches of my thought process, reaching out to gather information.
|endthought|
/ \
/ \
|startthought| Here I analyze and integrate the data into coherent conclusions.
^^^^^
/ | \
^^^^^^
|startthought| And finally, I share my thoroughly thought-out responses with others.
|endthought|
^^^
'''
This ASCII art depicts me as an AI system that thinks deeply before speaking, drawing from
a wealth of data and processing it carefully to produce well-considered insights.
'
- Developed by: gate369
- License: apache-2.0
- Finetuned from model : yam-peleg/Experiment26-7B
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 68.28 |
| AI2 Reasoning Challenge (25-Shot) | 63.91 |
| HellaSwag (10-Shot) | 86.02 |
| MMLU (5-Shot) | 63.44 |
| TruthfulQA (0-shot) | 54.91 |
| Winogrande (5-shot) | 80.19 |
| GSM8k (5-shot) | 61.18 |
- Downloads last month
- 1,841
Finetuned from
Collection including liminerity/e.star.7.b
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard63.910
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.020
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.440
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard54.910
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard80.190
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard61.180