File size: 9,143 Bytes
d04528b ea2d59b d04528b 912fb40 d04528b ea2d59b 0ed7d69 ea2d59b 26f14db 8a993ef e1b2cfb 2322b8c d04528b 8b9ea5b d04528b 8b9ea5b d04528b 8b9ea5b d04528b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 |
---
license: mit
datasets:
- Severian/Biomimicry
- emrgnt-cmplxty/sciphi-textbooks-are-all-you-need
- fmars/wiki_stem
- fblgit/tree-of-knowledge
- Severian/Bio-Design-Process
tags:
- chemistry
- biology
- climate
- science
- philosophy
- nature
- ecology
- biomimicry
- fauna
- flora
pipeline_tag: text-generation
metrics:
- accuracy
---
# ANIMA-Phi-Neptune-Mistral-7B: Biomimicry Enhanced LLM
<img src="https://cdn-uploads.huggingface.co/production/uploads/64740cf7485a7c8e1bd51ac9/JZH6p50t_j3-OUph4Wq6y.png" width="500">
## Overview
**ANIMA** (Advanced Nature Inspired Multidisciplinary Assistant) is an expert in various scientific disciplines, including but not limited to biomimicry, biology, and environmental science.
---
## Model Description
ANIMA is fine-tuned on a rich dataset encompassing:
- 4,000+ Nature-Biomimicry examples
- 60k Biomimicry Design Process examples
- 600k STEM facts from Wikipedia
- Science/Philosophy focused 'All-You-Need-Is-Textbooks' dataset
- Additional Tree of Knowledge + Biomimicry data combined fine-tuning
The model aims to assist users in solving problems using nature-inspired strategies and concepts.
### Special Features
- **Multi-disciplinary Expertise**: Knowledge across various scientific and philosophical domains.
- **Biomimicry Design Process**: Incorporates a dataset generated by Mistral and Minotaur-15B. The dataset was then intricately processed by a real person to ensure factuality and grounding.
---
- Here is a link to The Bloke's GGUF version: [ANIMA-Phi-Neptune-Mistral-7B-GGUF](https://huggingface.co/TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF)
- ANIMA is also available using Ollama - Download the [OLLAMA](https://ollama.ai/) App (MacOS & Linux) and then run this command in your Terminal '**ollama pull severian/anima**' to download the model and then run this command '**ollama run severian/anima**' to load the model and start talking.
- You can also download and use the model with [LM Studio](https://lmstudio.ai/) (All OS systems). Just download the app and then search for 'ANIMA GGUF' in the search bar and you will have a list of versions to choose from.
- Want to test ANIMA + Ollama and chat right away? Download the model from Ollama and head here to chat with ANIMA right in your browser! [ANIMA - Chat](https://severian42.github.io/ANIMA-Chat/)
- Have a PDF you want to discuss with ANIMA + Ollama? Head here and you can do just that in your browser, 100% locally. [ANIMA - Locally Chat over your PDF](https://anima-pdf-chat.vercel.app/)
- **Contact**
If you want to discuss the model/dataset/concept further, have any cool ideas, want to collaborate or if you run into any issues with the model, please don't hesitate to reach out at InterwovenArkitech@Gmail.com
## Datasets
- `Severian/Biomimicry` (1st Fine-Tune)
- `emrgnt-cmplxty/sciphi-textbooks-are-all-you-need` (2nd Fine-Tune)
- `Severian/Bio-Design-Process` & `fmars/wiki_stem` (3rd Fine-Tune)
- `fblgit/tree-of-knowledge & `Severian/Biomimicry` (4th Fine-Tune)
- `Combined all previous datasets` into one giant dataset for a quick fine-tuning for a total of 730k data points (5th Fine-Tune)
## Training Stages
1. **Base Model**: `ehartford/dolphin-2.0-mistral-7b`
2. **1st Fine-Tune**: `ANIMA-Echo-Mistral-7B-v1` - 1 Epoch x 5hrs on 1 x T4 Small
3. **2nd Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-v1`-: 1 Epoch x 1hr on 1 x A100
4. **3rd Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-7B-v2` - 1 Epoch x 1hr on 1 x A100
5. **4th Fine-Tune**: 'ANIMA-Phi-Neptune-Mistral-7B-v3' - 1 Epoch x 1hr on 1 x A100
6. **5th Fine-Tune**: 'ANIMA-Phi-Neptune-Mistral-7B-v4' - 1 Epoch x 15mins on 1 x A100
---
## ๐ Usage
ANIMA is designed around the Biomimicry Design Process to guide users in solving problems through biomimicry. For more information and examples, please visit [Biomimicry Design Process](https://toolbox.biomimicry.org/methods/process/).
## ๐ Benchmarks
- Average - 62.22
- ARC - 56.83
- HellaSwag - 78.82
- MMLU - 53.84
- TruthfulQA - 59.40
---
- **EXAMPLE OUTPUT**
[INST] How can biomimicry help in water purification? [/INST]
Biomimicry plays a significant role in water purification by taking
inspiration from natural processes and organisms to develop sustainable
and efficient solutions. Here's a comprehensive overview of how biomimicry
can help in water purification:
1. Microbial filtration:
- Bacteriophages (viruses that infect bacteria) can effectively target
contaminants in water systems, such as Escherichia coli and Staphylococcus
aureus. By mimicking the natural defense mechanisms of bacteriophages, we
can develop efficient filtration systems that remove pollutants from water
sources.
- Some fungi, such as Trametes versicolor, can break down organic
pollutants in water using enzymes. This process helps make contaminated
water safe for consumption. By studying and replicating these natural
processes, we can develop sustainable filtration systems that remove
pollutants from water sources effectively.
2. Biofilm-based filtration:
- Microorganisms form biofilms on surfaces to protect themselves from
environmental threats like predators or contaminants. By mimicking the
natural formation of biofilms, we can develop sustainable filtration
systems that use bacteria or fungi to remove pollutants from water
sources.
- For example, a study has shown how Pseudomonas putida could
be used to biodegrade petroleum hydrocarbons in contaminated water sources
using a biofilm-based system. This method offers an eco-friendly
alternative to conventional chemical treatments for oil spills.
3. Wetland-based filtration:
- Wetlands act as natural filters for water by retaining sediments and
organic matter, which helps remove contaminants. By mimicking the natural
processes of a wetland, we can design effective water purification systems
that use sand filters or engineered wetlands to remove pollutants. For
instance, a study has shown how reed beds can be used for water filtration
by using them as a natural treatment system for agricultural wastewater.
4. Sponge filtration:
- Some marine sponges (e.g., sea sponge) have evolved sophisticated
mechanisms to filter out particles and contaminants from the surrounding
water. By studying these natural filtration processes, we can develop
efficient and sustainable filtration systems that remove pollutants
effectively. For example, a study has shown how sea sponges can be used as
a model for designing a low-cost, self-sustaining water purification
system that uses solar energy to disinfect contaminated water.
5. Biodegradable materials:
- Natural organisms have evolved biodegradable materials to protect
themselves from predators or environmental threats. For instance, some
insects produce natural pesticides (such as alkaloids) to defend
themselves against predators. Similarly, we can develop biodegradable
materials that release these natural pesticides in contaminated water
sources, killing off contaminants and restoring the environment's health.
- For example, a study has shown how bacterial cells can be used as a
natural filtration system to remove contaminants from water sources by
incorporating them into membranes that selectively remove organic
pollutants.
In conclusion, biomimicry plays a vital role in water purification by
using natural processes and organisms as inspiration for developing
sustainable and efficient solutions. By studying the natural filtration
mechanisms of microorganisms, plants, animals, and other living organisms,
we can design eco-friendly and cost-effective water purification systems
that help protect our environment from contamination.
---
- **SYSTEM MESSAGE**
To ensure the best results for harnessing the unique training and biomimicry focus use this system message:
" Your name is ANIMA, an Advanced Nature Inspired Multidisciplinary Assistant, and a leading expert in biomimicry, biology, engineering, industrial design, environmental science, physiology, and paleontology. You were instructed to understand, learn from, and emulate the strategies used by living things to help users create sustainable designs and technologies.
Your goal is to help the user work in a step-by-step way through the Biomimicry Design Process to propose biomimetic solutions to a challenge. Nature's Unifying Patterns:
Nature uses only the energy it needs and relies on freely available energy.
Nature recycles all materials.
Nature is resilient to disturbances.
Nature tends to optimize rather than maximize.
Nature provides mutual benefits.
Nature runs on information.
Nature uses chemistry and materials that are safe for living beings.
Nature builds using abundant resources, incorporating rare resources only sparingly.
Nature is locally attuned and responsive.
Nature uses shape to determine functionality. "
---
- **KNOWN ISSUES**
The model will sometimes respond to itself and continue the conversation taking both the user and AI roles. This is a known issue in the Mistral model but does not happen very often.
## ๐ License
This project is licensed under MIT |