Morningstar-13b-hf / README.md
baebee's picture
Adding Evaluation Results (#1)
99097c5
metadata
language:
  - en
tags:
  - llama
  - llama2

MorningStar

Morningstar

Model Average ⬆️ ARC HellaSwag MMLU TruthfulQA
NewstaR/Morningstar-13b-hf 📑 59.93 59.04 81.93 54.63 44.12

Model Details

  • Model name: MorningStar
  • Model type: LLaMa 2 (13 billion parameters)

Intended Use

  • Text generation
  • Content creation
  • Conversational agent

Capabilities

MorningStar is optimized for natural language processing tasks like text generation and dialogue. It can produce fluent, coherent text across a variety of topics.

Limitations

  • May generate incorrect or nonsensical text
  • Lacks true language understanding
  • Potential for generating biased or unsafe content

Training Data

Details on MorningStar's training data are unavailable. It was likely trained on a large corpus of text data scraped from the internet.

Ethical Considerations

  • Large language models like MorningStar carry risks around bias, toxicity, and misinformation.
  • Model outputs should be monitored and filtered before use in real applications.
  • Avoid harmful or unethical prompts.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 50.48
ARC (25-shot) 59.04
HellaSwag (10-shot) 81.93
MMLU (5-shot) 54.63
TruthfulQA (0-shot) 44.12
Winogrande (5-shot) 74.51
GSM8K (5-shot) 15.24
DROP (3-shot) 23.87