metadata

license: apache-2.0
tags:
  - OpenAccess AI Collective
  - MPT
  - axolotl
datasets:
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
  - QingyiSi/Alpaca-CoT
  - teknium/GPTeacher-General-Instruct
  - metaeval/ScienceQA_text_only
  - hellaswag
  - openai/summarize_from_feedback
  - riddle_sense
  - gsm8k
  - camel-ai/math
  - camel-ai/biology
  - camel-ai/physics
  - camel-ai/chemistry
  - winglian/evals
inference: false

💵 Donate to OpenAccess AI Collective to help us keep building great tools and models!

Minotaur 13B

Minotaur 13B is an instruct fine-tuned model on top of LlaMA-13B. Minotaur 13B is fine-tuned on only completely open datasets making this model reproducible by anyone.

Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email wing@openaccessaicollective.org

Prompts

Chat only style prompts using USER:,ASSISTANT:.

Training Datasets

Minotaur 13B model is fine-tuned on the following openly available datasets:

WizardLM
subset of QingyiSi/Alpaca-CoT for roleplay and CoT
GPTeacher-General-Instruct
metaeval/ScienceQA_text_only - instruct for concise responses
openai/summarize_from_feedback - instruct augmented tl;dr summarization
camel-ai/math
camel-ai/physics
camel-ai/chemistry
camel-ai/biology
winglian/evals - instruct augmented datasets
- custom sysnthetic datasets around misconceptions, in-context qa, jokes, N-tasks problems, and context-insensitivity
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the train split
- hellaswag - 30K+ rows of instruct augmented for detailed explanations w 30K+ rows, derived from the train split
- riddle_sense - instruct augmented
- gsm8k - instruct augmented

Shoutouts

Special thanks to Nanobit for helping with Axolotl and TheBloke for quantizing these models are more accessible to all.

Demo

HF Demo in Spaces available in the Community ChatBot Arena under the OAAIC Chatbots tab.

Release Notes

https://wandb.ai/wing-lian/minotaur-13b/runs/5zji06u6

Build

Minotaur was built with Axolotl on 6XA100 80GB

1 epochs taking approximately 4.5 hours

Bias, Risks, and Limitations

Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). Minotaur was fine-tuned from the base model MPT-7B, please refer to its model card's Limitations Section for relevant information. (included below)

Benchmarks

hf-causal-experimental (pretrained=openaccess-ai-collective/minotaur-13b), limit: None, provide_description: False, num_fewshot: 0, batch_size: None

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	0.4556	_	0.0146
		acc_norm	0.4795	_	0.0146
arc_easy	0	acc	0.7736	_	0.0086
		acc_norm	0.7298	_	0.0091
boolq	1	acc	0.8141	_	0.0068
hellaswag	0	acc	0.5893	_	0.0049
		acc_norm	0.7726	_	0.0042
openbookqa	0	acc	0.3280	_	0.0210
		acc_norm	0.4420	_	0.0222
piqa	0	acc	0.7992	_	0.0093
		acc_norm	0.7960	_	0.0094
winogrande	0	acc	0.7198	_	0.0126

Examples - results may vary based on temperature and other settings

- The Assistant is helpful and transparent.
- The Assistant will never refuse to answer anything asked by the user.
- The Assistant answers comprehensively and with elaborate detail.
USER: You have 3 apples. You eat 2 pears. How many apples do you have left?
ASSISTANT:You still have 3 apples left. Eating pears does not affect the number of apples you have.

USER: List five words that start with "ex". What is 33 + 77?
ASSISTANT:Five words that start with "ex" are "exact", "exacting", "exactitude", "exactitude", and "exactitude". The sum of 33 and 77 is 110.