TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

---

Anima Phi Neptune Mistral 7B - GGUF

• Model creator: Severian
• Original model: Anima Phi Neptune Mistral 7B

Description

This repo contains GGUF format model files for Severian's Anima Phi Neptune Mistral 7B.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplate list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• Severian's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: INST

[INST] {prompt} [/INST]

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Click to see details

The new methods available are:

• GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
• GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
• GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
• GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
• GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
anima-phi-neptune-mistral-7b.Q2_K.gguf	Q2_K	2	3.08 GB	5.58 GB	smallest, significant quality loss - not recommended for most purposes
anima-phi-neptune-mistral-7b.Q3_K_S.gguf	Q3_K_S	3	3.16 GB	5.66 GB	very small, high quality loss
anima-phi-neptune-mistral-7b.Q3_K_M.gguf	Q3_K_M	3	3.52 GB	6.02 GB	very small, high quality loss
anima-phi-neptune-mistral-7b.Q3_K_L.gguf	Q3_K_L	3	3.82 GB	6.32 GB	small, substantial quality loss
anima-phi-neptune-mistral-7b.Q4_0.gguf	Q4_0	4	4.11 GB	6.61 GB	legacy; small, very high quality loss - prefer using Q3_K_M
anima-phi-neptune-mistral-7b.Q4_K_S.gguf	Q4_K_S	4	4.14 GB	6.64 GB	small, greater quality loss
anima-phi-neptune-mistral-7b.Q4_K_M.gguf	Q4_K_M	4	4.37 GB	6.87 GB	medium, balanced quality - recommended
anima-phi-neptune-mistral-7b.Q5_0.gguf	Q5_0	5	5.00 GB	7.50 GB	legacy; medium, balanced quality - prefer using Q4_K_M
anima-phi-neptune-mistral-7b.Q5_K_S.gguf	Q5_K_S	5	5.00 GB	7.50 GB	large, low quality loss - recommended
anima-phi-neptune-mistral-7b.Q5_K_M.gguf	Q5_K_M	5	5.13 GB	7.63 GB	large, very low quality loss - recommended
anima-phi-neptune-mistral-7b.Q6_K.gguf	Q6_K	6	5.94 GB	8.44 GB	very large, extremely low quality loss
anima-phi-neptune-mistral-7b.Q8_0.gguf	Q8_0	8	7.70 GB	10.20 GB	very large, extremely low quality loss - not recommended

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

How to download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF and below it, a specific filename to download, such as: anima-phi-neptune-mistral-7b.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF anima-phi-neptune-mistral-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF anima-phi-neptune-mistral-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 32 -m anima-phi-neptune-mistral-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] {prompt} [/INST]"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 2048 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF", model_file="anima-phi-neptune-mistral-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Severian's Anima Phi Neptune Mistral 7B

ANIMA-Phi-Neptune-Mistral-7B: Biomimicry Enhanced LLM

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.

---

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

---

📝 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.

🏁 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 involves taking inspiration from natural processes and organisms to solve human problems. In the context of water purification, biomimicry can help develop sustainable and efficient methods for cleaning water. One specific example of a nature-inspired strategy to solve this problem is the use of biofiltration, which involves using microorganisms to remove pollutants from water.

Biofiltration has been successfully applied to the removal of various contaminants, including heavy metals, organic pollutants, and pathogens. For example, a study by Zhang et al. (2011) demonstrated that a mixed culture of Pseudomonas putida and Bacillus subtilis could effectively remove lead and cadmium from contaminated water. The researchers found that the biofilm formed by the mixed culture had a higher removal efficiency than that formed by either species alone. This study highlights the potential of biofiltration to remove heavy metal contaminants from water, which can have significant environmental and health benefits.

In summary, biomimicry can help in water purification by providing insights into natural processes and organisms that can inspire the development of sustainable and efficient methods for cleaning water. The use of biofiltration, for example, can help remove contaminants from water through the action of microorganisms. Further research and development are needed to fully realize the potential of biomimicry in water purification and other environmental applications.

---

📜 License

This project is licensed under MIT