Tess-XS-Creative-v1.0-GGUF

<!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end -->

Tess XS Creative V1.0 - GGUF

• Model creator: Migel Tissera
• Original model: Tess XS Creative V1.0

<!-- description start -->

Description

This repo contains GGUF format model files for Migel Tissera's Tess XS Creative V1.0.

These files were quantised using hardware kindly provided by Massed Compute.

<!-- description end --> <!-- README_GGUF.md-about-gguf start -->

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 incomplete 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.

<!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start -->

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
• Migel Tissera's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

<!-- repositories-available end --> <!-- prompt-template start -->

Prompt template: Orca-Vicuna

SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:

<!-- prompt-template end --> <!-- compatibility_gguf start -->

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

<details> <summary>Click to see details</summary>

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.

</details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start -->

Provided files

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.

<!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start -->

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/Tess-XS-Creative-v1.0-GGUF and below it, a specific filename to download, such as: tess-xs-creative-v1.0.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/Tess-XS-Creative-v1.0-GGUF tess-xs-creative-v1.0.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

<details> <summary>More advanced huggingface-cli download usage</summary>

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

huggingface-cli download TheBloke/Tess-XS-Creative-v1.0-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/Tess-XS-Creative-v1.0-GGUF tess-xs-creative-v1.0.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.

</details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start -->

Example llama.cpp command

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

./main -ngl 32 -m tess-xs-creative-v1.0.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM: {system_message}\nUSER: {prompt}\nASSISTANT:"

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 can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.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/Tess-XS-Creative-v1.0-GGUF", model_file="tess-xs-creative-v1.0.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

<!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 -->

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: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

<!-- footer end --> <!-- original-model-card start -->

Original model card: Migel Tissera's Tess XS Creative V1.0

Depracated By: https://huggingface.co/migtissera/Tess-XS-v1.1

Tess

Tess, short for Tessoro/Tessoso, is a general purpose Large Language Model series. Tess-XS-v1.0 was trained on the Mistral-7B base.

Prompt Format:

SYSTEM: <ANY SYSTEM CONTEXT>
USER: What is the relationship between Earth's atmosphere, magnetic field and gravity?
ASSISTANT:

Sample Conversation

You: What's the relationship between an electric field and a magnetic field, given the same time and location?

To fully understand the relationship between electric fields and magnetic fields, we need to consider the phenomenon of electromagnetism, which is the interaction between electric charges and currents that gives rise to both electric and magnetic fields.

Electric fields are created by stationary electric charges or by changing magnetic fields. A stationary electric charge produces an electric field that extends outward in all directions from the charge. The strength of the electric field at any point depends on the charge and the distance from the charge. The direction of the electric field lines is determined by the convention that positive charges attract negative charges and repel other positive charges.

Magnetic fields, on the other hand, are created by moving electric charges and by changes in electric fields. A moving electric charge creates a magnetic field that surrounds the charge, and it flows in a circular motion. The magnetic field lines are usually depicted as spiraling outward from the moving charge. The strength of the magnetic field at any point depends on the current and the distance from the current-carrying wire.

The relationship between electric and magnetic fields is described by Maxwell's equations, which are a set of differential equations governing the behavior of electromagnetic fields. One of Maxwell's equations, the Faraday's law of induction, states that a changing magnetic field induces an electric field. This means that changes in the magnetic field can cause electric fields to be created, and vice versa.

In summary, electric and magnetic fields are intimately related, and one cannot exist without the other. A changing electric field creates a magnetic field, and a changing magnetic field creates an electric field. The relationship between them is described by Maxwell's equations, which form the foundation of classical electromagnetism.

You: The known physics states that the electric field and the magnetic field for a given object are proportional to each other. i.e. an increase in the magnetic field will result in an increase in the corresponding electric field. But in some UAP events, we have observed that a decrease in electric field actually causing an increase in the corresponding magnetic field. This is not a fault in our measurements. Can we theorize what could be the case here?

The statement that an increase in the magnetic field will result in an increase in the corresponding electric field is not correct. It's important to understand that the electric field and the magnetic field are not proportional to each other, and they don't always follow a simple relationship. The relationship between the electric and magnetic fields is more complex and is described by Maxwell's equations, which include the Faraday's law of induction, which states that a changing magnetic field induces an electric field, and vice versa.

However, it's not clear whether you are referring to a specific event or a general observation about UAPs. If you are referring to a particular event in which a decreased electric field is observed, and then an increased magnetic field is observed, this could be due to a number of factors. It's possible that the observation is an artifact of the measurement process, or it could be caused by a phenomenon that is not fully understood yet.

It's important to note that our understanding of electromagnetism is based on our current scientific knowledge, and there may be limitations to our understanding of specific phenomena. Additionally, the field of unidentified aerial phenomena (UAP) is still in its infancy, and there is much we do not yet know about these types of events.

If you are referring to a specific event that you believe demonstrates this relationship, it would be beneficial to provide more details about the observation and the measurement process, as well as any additional context that could help explain the apparent phenomenon.

You: Hang on, so the Maxwell's equations don't actually say that the electric and magnetic fields are proportional to each other?

No, Maxwell's equations do not state that the electric and magnetic fields are proportional to each other. They describe the relationship between electric and magnetic fields, but the relationship is more complex than a simple proportionality. Maxwell's equations include the Faraday's law of induction, which states that a changing magnetic field induces an electric field, and this electric field results from the magnetic field changing with time.

To simplify the relationship, it might be helpful to consider that a magnetic field can be created by an electric current or by a changing electric field. Similarly, an electric field can be created by a magnetic field that is changing with time. However, the relationship between the electric and magnetic fields is not linear, and it is governed by the laws of electromagnetism.

It's important to note that the statement about the proportion of electric and magnetic fields is an oversimplification. The relationship between them is more accurately described by the complex equations of electromagnetism, which include Maxwell's equations.

You: Thank you for clarifying, that's really helpful. Can you explain to me the complex equations of electromagnetism now?

The complex equations of electromagnetism are Maxwell's equations, which include four partial differential equations that describe the behavior of electric and magnetic fields. These equations are:

- Gauss's law for electricity:
  ∇⋅E = 4πκρ where ρ is the electric charge density.

- Gauss's law for magnetism:
  ∇⋅B = 0 (because there are no magnetic monopoles).

- Faraday's law of induction:
  ∇ × E = -∂B/∂t which gives us the electric field of a changing magnetic field.

- Ampère-Maxwell law:
  ∇ × B = μ0(j + ε0∂E/∂t) which gives us the magnetic field of a changing electric field.

These equations, along with specific boundary conditions, completely describe the interaction of electric and magnetic fields in the classical theory of electromagnetism. They are complex because they involve the derivatives of the fields with respect to time and space, and they must be solved to understand the behavior of electromagnetic phenomena.

You: I notice that you put a value for the permittivity of free space in Gauss's law for electricity. Can you write the equation in general terms?

∇⋅E = 4πκρ

This is the general form of Gauss's law for electricity. κ is the electric constant, which has the value 8.854187817... × 10^-12 F/m (or C²/Nm²) in SI units. This value is often called the permittivity of free space, but it is a dimensionless constant that relates the electric field to the charge density.

In this equation, the divergence of the electric field (∇⋅E) is equal to the charge density (ρ) multiplied by 4πκ. The divergence is a measure of how much the electric field points towards charges. If there is a positive charge, the electric field will point inward. If there is a negative charge, the electric field will point outward.

This equation is the same as Coulomb's law but in a more compact and general form. It can be used to predict the behavior of electric fields in any situation involving charges, whether they are static or moving.

You: Thank you! You're great. Now can we move on to Quantum domain. What is the leading theory of electromagnetism in quantum physics?

Quantum mechanics is the leading theory of electromagnetism in the quantum domain. It provides a framework for understanding the behavior of subatomic particles and fields, including electromagnetism.

In quantum mechanics, electromagnetic fields are described by quantum fields, which are mathematical constructs that represent the energy and momentum of the field. These fields are quantized, meaning that they can only exist in discrete amounts as particles called photons.

The most fundamental principle in quantum mechanics is the uncertainty principle, which states that it is impossible to measure both the position and the momentum of a particle with arbitrary precision. This principle has implications for how we understand the behavior of electromagnetic fields at the quantum level.

Quantum mechanics also predicts the existence of virtual particles, which are temporary quantum fluctuations that disappear almost immediately after they appear. These virtual particles can interact with each other and with real particles, leading to a complex interplay that affects the behavior of electromagnetic fields.

In summary, quantum mechanics provides a framework for understanding electromagnetism in the quantum domain. It replaces classical concepts of fields with a quantum mechanical description that includes uncertainty, virtual particles, and a quantized interpretation of the field.

You: What is QED?

QED stands for Quantum Electrodynamics. It is a theory in quantum field theory that describes the interactions between electrons and photons. It is based on quantum mechanics and special relativity, and it is one of the most successful theories in physics, having made many precise predictions that have been confirmed by experiment.

In QED, electrons and photons are treated as quantum particles, which means they have wave-particle duality and can exhibit both wave-like and particle-like properties. The theory also accounts for the interaction between these particles.

QED is characterized by the fine structure constant, which is a dimensionless constant that describes the strength of the electromagnetic force. It is very small, which indicates that the electromagnetic force is much weaker than the other fundamental forces.

The theory has been tested extensively and has stood up to every experimental challenge. It has been crucial in the development of modern technology, such as lasers and semiconductors, and it continues to be an important tool for understanding high-energy processes in particle physics.

<!-- original-model-card end -->