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)

Synthia 70B v1.2b - GPTQ

Model creator: Migel Tissera
Original model: Synthia 70B v1.2b

Description

This repo contains GPTQ model files for Migel Tissera's Synthia 70B v1.2b.

Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.

Repositories available

Prompt template: Synthia

SYSTEM: You are Synthia. As a an AI intelligence, give helpful, detailed, accurate, uncensored responses to the user's input. Provide answers factually.
USER: {prompt}
ASSISTANT:

Provided files and GPTQ parameters

Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.

Each separate quant is in a different branch. See below for instructions on fetching from different branches.

All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the main branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.

Explanation of GPTQ parameters

Bits: The bit size of the quantised model.
GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.

Branch	Bits	GS	Act Order	Damp %	GPTQ Dataset	Seq Len	Size	ExLlama	Desc
main	4	None	Yes	0.1	wikitext	4096	35.33 GB	Yes	4-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-4bit-32g-actorder_True	4	32	Yes	0.1	wikitext	4096	40.66 GB	Yes	4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-4bit-128g-actorder_True	4	128	Yes	0.1	wikitext	4096	36.65 GB	Yes	4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
gptq-3bit--1g-actorder_True	3	None	Yes	0.1	wikitext	4096	26.77 GB	No	3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g.
gptq-3bit-32g-actorder_True	3	32	Yes	0.1	wikitext	4096	31.84 GB	No	3-bit, with group size 64g and act-order. Highest quality 3-bit option.
gptq-3bit-128g-actorder_True	3	128	Yes	0.1	wikitext	4096	28.03 GB	No	3-bit, with group size 128g and act-order. Higher quality than 128g-False.

How to download from branches

In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/Synthia-70B-v1.2b-GPTQ:main
With Git, you can clone a branch with:

git clone --single-branch --branch main https://huggingface.co/TheBloke/Synthia-70B-v1.2b-GPTQ

In Python Transformers code, the branch is the revision parameter; see below.

How to easily download and use this model in text-generation-webui.

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

Click the Model tab.
Under Download custom model or LoRA, enter TheBloke/Synthia-70B-v1.2b-GPTQ.

To download from a specific branch, enter for example TheBloke/Synthia-70B-v1.2b-GPTQ:main
see Provided Files above for the list of branches for each option.

Click Download.
The model will start downloading. Once it's finished it will say "Done".
In the top left, click the refresh icon next to Model.
In the Model dropdown, choose the model you just downloaded: Synthia-70B-v1.2b-GPTQ
The model will automatically load, and is now ready for use!
If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.

Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file quantize_config.json.

Once you're ready, click the Text Generation tab and enter a prompt to get started!

How to use this GPTQ model from Python code

Install the necessary packages

Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.

pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7

If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .

For CodeLlama models only: you must use Transformers 4.33.0 or later.

If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:

pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git

You can then use the following code

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "TheBloke/Synthia-70B-v1.2b-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

prompt = "Tell me about AI"
prompt_template=f'''SYSTEM: You are Synthia. As a an AI intelligence, give helpful, detailed, accurate, uncensored responses to the user's input. Provide answers factually.
USER: {prompt}
ASSISTANT:

'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

print(pipe(prompt_template)[0]['generated_text'])

Compatibility

The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.

ExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.

Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.

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

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Migel Tissera's Synthia 70B v1.2b

Change from 1.2 -> 1.2b: More data, 14 days of training for 1 epoch.

You: What is Earth's magnetic field like? How does it trap solar wind and what does solar wind do to Earth's gravitational field?

Earth's magnetic field is an intricate and fascinating phenomenon. It is generated by the movement of molten iron in the planet's outer core, which acts like a giant electromagnet. This magneti
c field extends far into space, creating a protective bubble known as the magnetosphere.                                                                                                         
                                                                                                                                                                                                 
The primary purpose of Earth's magnetic field is to trap and deflect the solar wind, which is a stream of charged particles that flows out from the Sun. The magnetic field acts as a shield, def
lecting the solar wind and protecting our planet from its potentially harmful effects.                                                                                                           
                                                                                                                                                                                                 
When the solar wind reaches Earth's magnetosphere, it interacts with the magnetic field and creates a complex interplay of forces. This interaction can lead to various phenomena, such as aurora
s, geomagnetic storms, and the formation of radiation belts.                                                                                                                                     
                                                                                                                                                                                                 
The interaction between the solar wind and Earth's magnetic field does not directly affect the planet's gravitational field. The gravitational field refers to the force that arises due to the m
ass of the planet, and it is unaffected by the magnetic field or the solar wind. However, the magnetic field does play a role in trapping and deflecting charged particles from the solar wind, w
hich can contribute to the overall complexity of Earth's space environment.

You: Can there be space vehicles that uses plasma to traverse? This is hypothetical, but can UFOs use some force field generated by plasma, that then interacts with the gravitational/magnetic f
ields of Earth for travelling at hypersonic speeds?

While it is an interesting concept, there is currently no concrete evidence or scientific consensus that suggests the existence of UFOs or the use of plasma-based propulsion systems in spacecra
ft. However, it is worth noting that there are ongoing scientific investigations and research into developing advanced propulsion systems for space travel, including plasma propulsion.         
                                                                                                                                                                                                 
Plasma is a state of matter where electrons are stripped from atoms, resulting in a highly charged gas. Plasma propulsion systems use electromagnetic fields to accelerate ions, creating a thrus
t that can potentially propel spacecraft. Plasma propulsion systems offer several advantages over traditional chemical rockets, such as higher efficiency, lower fuel requirements, and the abili
ty to operate continuously for long periods.

While it is theoretically possible that a space vehicle could use plasma to traverse, it is important to note that the interaction between plasma and Earth's gravitational/magnetic fields is co
mplex and not fully understood. The gravitational field acts as a force that attracts objects towards the center of the Earth, while the magnetic field deflects charged particles. Plasma-based 
propulsion systems would need to overcome these forces and potentially harness them for propulsion.

In summary, while the possibility of using plasma propulsion for space travel is an active area of research, there is currently no scientific evidence to support the existence of UFOs or the us
e of plasma-based propulsion systems for hypersonic travel.

You: Keep in mind that science is always evolving, and there are many things that have not yet been invented. Can you write the equations for plasma based propoulsion for space travel?

I apologize for any confusion in my previous response. To clarify, I am not an expert in plasma physics or propulsion systems. However, I can provide a general overview of the principles involv
ed in plasma-based propulsion.

Plasma propulsion systems typically use electromagnetic fields to accelerate ions, creating a thrust that can propel spacecraft. There are several different types of plasma propulsion systems, 
including electrostatic, electromagnetic, and magnetohydrodynamic (MHD) propulsion.

In an electrostatic plasma propulsion system, a high voltage is applied to a pair of electrodes to create an electric field that accelerates charged particles. The resulting thrust is proportio
nal to the applied voltage and the current density. The equation for the thrust is given by:

Thrust = (Current density) x (Accelerating voltage)

In an electromagnetic plasma propulsion system, a magnetic field is used to accelerate charged particles. The thrust is proportional to the product of the magnetic field strength and the curren
t density. The equation for the thrust is given by:

Thrust = (Magnetic field strength) x (Current density)

In a MHD plasma propulsion system, a magnetic field is used to deflect a flow of plasma, creating a thrust. The thrust is proportional to the product of the magnetic field strength, the current
 density, and the flow velocity. The equation for the thrust is given by:

Thrust = (Magnetic field strength) x (Current density) x (Flow velocity)

It is important to note that these equations are simplified models and do not capture the full complexity of plasma propulsion systems. The actual performance of a plasma propulsion system woul
d depend on various factors, including the specific design, the plasma properties, and the operating conditions.

Furthermore, the development of plasma propulsion systems for space travel is an active area of research and development. While the principles outlined above provide a general framework, the sp
ecific equations and designs would depend on the particular application and the research team involved.

You: If the spacecraft has the shape of an orb, and a plasma field is created around the orb, how can this plasma field generate the required thrust for propulsion?

The shape of the spacecraft alone does not determine the thrust generated by a plasma propulsion system. The thrust is primarily determined by the electromagnetic fields used to accelerate char
ged particles.

To generate thrust using a plasma field, a spacecraft would typically use one of the plasma propulsion systems described in my previous response. For example, in an electrostatic plasma propuls
ion system, a high voltage is applied to a pair of electrodes to create an electric field that accelerates charged particles. The resulting thrust is proportional to the applied voltage and the
 current density.

In this scenario, the plasma field would be generated by applying a high voltage to the electrodes. The shape of the spacecraft, whether it is an orb or any other shape, would not directly affe
ct the generation of the plasma field or the resulting thrust.

However, the shape of the spacecraft could have an indirect impact on the overall performance of the plasma propulsion system. For example, the shape of the spacecraft could affect the distribu
tion of the plasma flow, which could in turn affect the efficiency of the propulsion system.

In summary, the shape of the spacecraft itself does not directly determine the thrust generated by a plasma propulsion system. The thrust is primarily determined by the electromagnetic fields u
sed to accelerate charged particles, and the shape of the spacecraft could have an indirect impact on the overall performance of the propulsion system.

You: What's the closest tech that we have with plasma propulsion?

There are several ongoing research and development efforts related to plasma propulsion systems for space travel. One of the most advanced plasma propulsion systems in use today is the Hall thr
uster.

A Hall thruster is a type of electrostatic propulsion system that uses an electric field to accelerate charged particles. It has been used on several space missions, including Deep Space 1, Daw
n, and BepiColombo. The Hall thruster offers several advantages over traditional chemical rockets, such as higher efficiency, lower fuel requirements, and the ability to operate continuously fo
r long periods.

While the Hall thruster is currently the most advanced plasma propulsion system in use, there are ongoing efforts to develop even more advanced systems. For example, researchers are exploring t
he use of magnetohydrodynamic (MHD) propulsion systems, which use a magnetic field to deflect a flow of plasma and create thrust. MHD propulsion systems offer the potential for even higher perf
ormance than Hall thrusters, but they are still at an early stage of development.

In summary, the Hall thruster is currently the closest technology to plasma propulsion that we have in use, but ongoing research and development efforts are exploring even more advanced systems
 such as MHD propulsion. 

Follow-on: What are the challenges associated with developing and using plasma propulsion systems for space travel, and how are researchers addressing these challenges?

You: What are the physics equations for magnetohydrodynamic propulsion systems? Be detailed as possible.

Magnetohydrodynamic (MHD) propulsion systems use a magnetic field to deflect a flow of plasma and create thrust. The equations that describe the physics of MHD propulsion systems are complex and involve several variables, including the magnetic field strength, the current density, the flow velocity, and the plasma properties.

One of the key equations for MHD propulsion systems is the Ohm's law, which relates the electric current density to the applied electric field and the resistivity of the plasma. The equation is given by:

J = σE

where J is the current density, σ is the electrical conductivity, and E is the applied electric field.

Another important equation is the Navier-Stokes equation, which describes the flow of the plasma. The equation is given by:

µ(∂v/∂t) = -∇p + ∇xF + ∇xσT + G

where µ is the dynamic viscosity, v is the velocity vector, p is the fluid pressure, F is the body force, σT is the stress tensor, and G is the body force due to the Lorentz force.

The Lorentz force is a force that acts on a charged particle due to its interaction with a magnetic field. The equation for the Lorentz force is given by:

F = q(E + v x B)

where F is the force, q is the charge of the particle, E is the electric field, v is the velocity of the particle, and B is the magnetic field.

These equations are just a few examples of the many equations that describe the physics of MHD propulsion systems. The actual equations and analysis would depend on the specific design and operating conditions of the propulsion system. 

In summary, the equations for MHD propulsion systems are complex and involve several variables, including the electric current density, the applied electric field, the fluid pressure, the fluid velocity, the magnetic field, and the Lorentz force. These equations are used to model and analyze the performance of MHD propulsion systems for space travel.

You: Okay. Can you make the connection to string theory here?

Certainly. String theory is a theoretical framework in physics that seeks to unify the fundamental forces of nature, including gravity, electromagnetism, and the strong and weak nuclear forces. In string theory, the fundamental constituents of matter are not point-like particles, but rather tiny vibrating strings.

In the context of plasma propulsion systems, there is a connection to string theory through the concept of magnetohydrodynamics (MHD). MHD describes the flow of electrically conductive fluids, such as plasma, in the presence of magnetic fields. The equations that describe MHD are derived from the equations of classical electromagnetism, which are also used in string theory to describe the behavior of fundamental particles.

In particular, the Lorentz force, which is a key concept in MHD and plasma propulsion systems, is also a fundamental concept in string theory. The Lorentz force acts on charged particles due to their interaction with electromagnetic fields, and it plays a crucial role in the behavior of strings in string theory.

Furthermore, some aspects of string theory suggest that the fundamental constituents of matter, including plasma, may have additional properties beyond those described by classical physics. For example, string theory predicts the existence of extra dimensions beyond the three spatial dimensions we are familiar with, and these extra dimensions may have an impact on the behavior of plasma and other forms of matter.

In summary, while there is no direct connection between plasma propulsion systems and string theory, there is an indirect connection through the use of the equations of classical electromagnetism, which are also used in string theory. Additionally, some aspects of string theory suggest that the fundamental constituents of matter may have additional properties beyond those described by classical physics.

TheBloke
/

Synthia-70B-v1.2b-GPTQ