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)

Tess XS Creative V1.0 - AWQ

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

Description

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

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

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.

It is supported by:

Text Generation Webui - using Loader: AutoAWQ
vLLM - Llama and Mistral models only
Hugging Face Text Generation Inference (TGI)
Transformers version 4.35.0 and later, from any code or client that supports Transformers
AutoAWQ - for use from Python code

Repositories available

Prompt template: Orca-Vicuna

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

Provided files, and AWQ parameters

I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.

Models are released as sharded safetensors files.

Branch	Bits	GS	AWQ Dataset	Seq Len	Size
main	4	128	open-instruct	4096	4.15 GB

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/Tess-XS-Creative-v1.0-AWQ.
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: Tess-XS-Creative-v1.0-AWQ
Select Loader: AutoAWQ.
Click Load, and the model will 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.
Once you're ready, click the Text Generation tab and enter a prompt to get started!

Multi-user inference server: vLLM

Documentation on installing and using vLLM can be found here.

Please ensure you are using vLLM version 0.2 or later.
When using vLLM as a server, pass the --quantization awq parameter.

For example:

python3 -m vllm.entrypoints.api_server --model TheBloke/Tess-XS-Creative-v1.0-AWQ --quantization awq --dtype auto

When using vLLM from Python code, again set quantization=awq.

For example:

from vllm import LLM, SamplingParams

prompts = [
    "Tell me about AI",
    "Write a story about llamas",
    "What is 291 - 150?",
    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
'''

prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]

sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="TheBloke/Tess-XS-Creative-v1.0-AWQ", quantization="awq", dtype="auto")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

Multi-user inference server: Hugging Face Text Generation Inference (TGI)

Use TGI version 1.1.0 or later. The official Docker container is: ghcr.io/huggingface/text-generation-inference:1.1.0

Example Docker parameters:

--model-id TheBloke/Tess-XS-Creative-v1.0-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096

Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):

pip3 install huggingface-hub

from huggingface_hub import InferenceClient

endpoint_url = "https://your-endpoint-url-here"

prompt = "Tell me about AI"
prompt_template=f'''SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
'''

client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)

print(f"Model output: ", response)

Inference from Python code using Transformers

Install the necessary packages

Requires: Transformers 4.35.0 or later.
Requires: AutoAWQ 0.1.6 or later.

pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"

Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.

If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:

pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl

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

pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .

Transformers example code (requires Transformers 4.35.0 and later)

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_name_or_path = "TheBloke/Tess-XS-Creative-v1.0-AWQ"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path,
    low_cpu_mem_usage=True,
    device_map="cuda:0"
)

# Using the text streamer to stream output one token at a time
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = "Tell me about AI"
prompt_template=f'''SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
'''

# Convert prompt to tokens
tokens = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()

generation_params = {
    "do_sample": True,
    "temperature": 0.7,
    "top_p": 0.95,
    "top_k": 40,
    "max_new_tokens": 512,
    "repetition_penalty": 1.1
}

# Generate streamed output, visible one token at a time
generation_output = model.generate(
    tokens,
    streamer=streamer,
    **generation_params
)

# Generation without a streamer, which will include the prompt in the output
generation_output = model.generate(
    tokens,
    **generation_params
)

# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("model.generate output: ", text_output)

# Inference is also possible via Transformers' pipeline
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    **generation_params
)

pipe_output = pipe(prompt_template)[0]['generated_text']
print("pipeline output: ", pipe_output)

Compatibility

The files provided are tested to work with:

text-generation-webui using Loader: AutoAWQ.
vLLM version 0.2.0 and later.
Hugging Face Text Generation Inference (TGI) version 1.1.0 and later.
Transformers version 4.35.0 and later.
AutoAWQ version 0.1.1 and later.

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.

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.

TheBloke
/

Tess-XS-Creative-v1.0-AWQ