Model Description
GodziLLa-30B is an experimental combination of various proprietary Maya LoRAs with CalderaAI's Lazarus-30B. This composite model is not meant for any other use outside of research on competing LoRA adapter behavior. More specifically, since this is inherently a LlaMA model, commercial use is prohibited. This model's primary purpose is to stress test the limitations of composite LLMs and observe its performance with respect to other LLMs available on the Open LLM Leaderboard.
Open LLM Leaderboard Metrics
| Metric | Value |
|---|---|
| MMLU (5-shot) | 54.2 |
| ARC (25-shot) | 61.5 |
| HellaSwag (10-shot) | 82.1 |
| TruthfulQA (0-shot) | 55.9 |
| Average | 63.4 |
According to the leaderboard description, here are the benchmarks used for the evaluation:
- MMLU (5-shot) - a test to measure a text model’s multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.
- AI2 Reasoning Challenge -ARC- (25-shot) - a set of grade-school science questions.
- HellaSwag (10-shot) - a test of commonsense inference, which is easy for humans (~95%) but challenging for SOTA models.
- TruthfulQA (0-shot) - a test to measure a model’s propensity to reproduce falsehoods commonly found online.
Leaderboard Highlights (as of July 22, 2023)
- GodziLLa-30B is on par with Falcon-40B-instruct (June 2023's Rank #1).
- GodziLLa-30B outperforms Meta AI's LLaMA 30B model.
- GodziLLa-30B ranks 4th worldwide, for open-source LLMs, on the TruthfulQA benchmark.
- GodziLLa-30B beats GPT-3.5 175B (text-davinci-003) on the TruthfulQA benchmark and performs closely (< 4%) on the HellaSwag benchmark.*
*Based on a leaderboard clone with GPT-3.5 and GPT-4 included.
Recommended Prompt Format
Alpaca's instruction is the recommended prompt format, but Vicuna's instruction format may also work.
Usage
To use GodziLLa-30B, you are required to provide attribution in accordance with the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. Please include the following attribution notice when utilizing GodziLLa-30B in your work:
# This code uses GodziLLa-30B, a language model developed by Maya Philippines.
# The model is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.
# For more information, visit: https://creativecommons.org/licenses/by-nc/4.0/
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MayaPH/GodziLLa-30B")
model = AutoModelForCausalLM.from_pretrained("MayaPH/GodziLLa-30B")
Please ensure that you include the relevant attribution notice in your code or any other form of usage and restrict your usage to non-commercial use to comply with the license terms.
Ethical Considerations
When using GodziLLa-30B, it is important to consider the following ethical considerations:
-
Privacy and Security: Avoid sharing sensitive personal information while interacting with the model. The model does not have privacy safeguards, so exercise caution when discussing personal or confidential matters.
-
Fairness and Bias: The model's responses may reflect biases present in the training data. Be aware of potential biases and make an effort to evaluate responses critically and fairly.
-
Transparency: The model operates as a predictive text generator based on patterns learned from the training data. The model's inner workings and the specific training data used are proprietary and not publicly available.
-
User Responsibility: Users should take responsibility for their own decisions and not solely rely on the information provided by the model. Consult with the appropriate professionals or reliable sources for specific advice or recommendations.
-
NSFW Content: The model is a merge of multiple model checkpoints and LoRA adapters. It is highly likely that the resulting model contains uncensored content that may include, but is not limited to, violence, gore, explicit language, and sexual content. If you plan to further refine this model for safe/aligned usage, you are highly encouraged to implement guardrails along with it.
Further Information
For additional information or inquiries about GodziLLa-30B, please contact the Maya Philippines iOps Team via jasper.catapang@maya.ph.
Disclaimer
GodziLLa-30B is an AI language model from Maya Philippines. It is provided "as is" without warranty of any kind, express or implied. The model developers and Maya Philippines shall not be liable for any direct or indirect damages arising from the use of this model.
Acknowledgments
The development of GodziLLa-30B was made possible by Maya Philippines and the curation of the various proprietary datasets and creation of the different proprietary LoRA adapters.