--- 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 --- [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) **[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/OpenAccess-AI-Collective) to help us keep building great tools and models!** # Minotaur 7B Minotaur 7B is an instruct fine-tuned model on top of LlaMA-13B. Minotaur 7B 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](https://discord.gg/PugNNHAF5r) or email [wing@openaccessaicollective.org](mailto:wing@openaccessaicollective.org) # Prompts Chat only style prompts using `USER:`,`ASSISTANT:`. minotaur # Training Datasets Minotaur 7B model is fine-tuned on the following openly available datasets: - [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered) - [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT) - [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct) - [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses - [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization - [camel-ai/math](https://huggingface.co/datasets/camel-ai/math) - [camel-ai/physics](https://huggingface.co/datasets/camel-ai/physics) - [camel-ai/chemistry](https://huggingface.co/datasets/camel-ai/chemistry) - [camel-ai/biology](https://huggingface.co/datasets/camel-ai/biology) - [winglian/evals](https://huggingface.co/datasets/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](https://huggingface.co/datasets/hellaswag) - 30K+ rows of instruct augmented for detailed explanations w 30K+ rows, derived from the `train` split - [riddle_sense](https://huggingface.co/datasets/riddle_sense) - instruct augmented, derived from the `train` split - [gsm8k](https://huggingface.co/datasets/gsm8k) - instruct augmented, derived from the `train` split - prose generation # 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](https://huggingface.co/spaces/openaccess-ai-collective/rlhf-arena) under the OAAIC Chatbots tab. ## Release Notes - https://wandb.ai/wing-lian/minotaur-13b/runs/ucgd0x6n ## Build Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8x RTXA6000 - 1 epochs taking approximately 1.5 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 LLaMA 13B, please refer to its model card's Limitations Section for relevant information. (included below) ## Benchmarks hf-causal-experimental (pretrained=openaccess-ai-collective/minotaur-7b), limit: None, provide_description: False, num_fewshot: 0, batch_size: None | Task |Version| Metric |Value | |Stderr| |-------------|------:|--------|-----:|---|-----:| |arc_challenge| 0|acc |0.4078|_ |0.0144| | | |acc_norm|0.4292|_ |0.0145| |arc_easy | 0|acc |0.7424|_ |0.0090| | | |acc_norm|0.6877|_ |0.0095| |boolq | 1|acc |0.7679|_ |0.0074| |hellaswag | 0|acc |0.5636|_ |0.0049| | | |acc_norm|0.7377|_ |0.0044| |openbookqa | 0|acc |0.3540|_ |0.0214| | | |acc_norm|0.4420|_ |0.0222| |piqa | 0|acc |0.7878|_ |0.0095| | | |acc_norm|0.7851|_ |0.0096| |winogrande | 0|acc |0.7072|_ |0.0128| ## Examples - results may vary based on temperature and other settings ``` The following is a chat between a USER and a friendly and helpful ASSISTANT. USER: You have 5 apples. You eat 3 pears. How many apples do you have left? ASSISTANT:You still have 5 apples because eating pears does not affect the number of apples you have. ``` ``` The following is a chat between a USER and a friendly and helpful ASSISTANT. USER: List three words that start with "ex". What is 33 + 77? ASSISTANT:Three words starting with the letter 'e' are excited, eatable, and expensive. 33+77 equals 106. ``` ``` The following is a chat between a USER and a friendly and helpful ASSISTANT. USER: Solve for x: 5x = 3x + 10 ASSISTANT:To solve the equation 5x = 3x + 10, we can follow these steps: Step 1: Add both sides of the equation to get a common denominator. (1/5)x = 1 (common) Subtract the term with "x" on both sides. -2/5 x = 10 Step 2: To solve the resulting equation, isolate the variable "x". First, multiply all terms by 5 to eliminate the fractions. 5x = 15 Now, divide the entire right side by 5. x = 15/5 Finally, simplify to get the solution in its simplest form. x = 1 So, the solution is x = 1. ``` Yup, 7B still sucks at math