README.md

metadata

inference: false
license: llama2
model_creator: Nick Perez
model_link: https://huggingface.co/nkpz/llama2-22b-daydreamer-v3
model_name: Llama2 22B Daydreamer2 v3
model_type: llama
quantized_by: TheBloke

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

Llama2 22B Daydreamer2 v3 - GPTQ

• Model creator: Nick Perez
• Original model: Llama2 22B Daydreamer2 v3

Description

This repo contains GPTQ model files for Nick Perez's Llama2 22B Daydreamer2 v3.

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

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

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

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 GPTQ files are made with AutoGPTQ.

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 issues with models that use Act Order plus Group Size.
• 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	128	No	0.1	wikitext	4096	11.99 GB	Yes	Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options.
gptq-4bit-32g-actorder_True	4	32	Yes	0.1	wikitext	4096	13.24 GB	Yes	4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed.
gptq-4bit-64g-actorder_True	4	64	Yes	0.1	wikitext	4096	12.40 GB	Yes	4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-4bit-128g-actorder_True	4	128	Yes	0.1	wikitext	4096	11.99 GB	Yes	4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit--1g-actorder_True	8	None	Yes	0.1	wikitext	4096	22.28 GB	No	8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed.
gptq-8bit-128g-actorder_True	8	128	Yes	0.1	wikitext	4096	22.77 GB	No	8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed.

How to download from branches

• In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/Llama2-22B-Daydreamer-v3-GPTQ:gptq-4bit-32g-actorder_True
• With Git, you can clone a branch with:

git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Llama2-22B-Daydreamer-v3-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 know how to make a manual install.

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/Llama2-22B-Daydreamer-v3-GPTQ.

• To download from a specific branch, enter for example TheBloke/Llama2-22B-Daydreamer-v3-GPTQ:gptq-4bit-32g-actorder_True
• see Provided Files above for the list of branches for each option.

3. Click Download.
4. The model will start downloading. Once it's finished it will say "Done"
5. In the top left, click the refresh icon next to Model.
6. In the Model dropdown, choose the model you just downloaded: Llama2-22B-Daydreamer-v3-GPTQ
7. The model will automatically load, and is now ready for use!
8. 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 set GPTQ parameters any more. These are set automatically from the file quantize_config.json.

9. 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

First make sure you have AutoGPTQ 0.3.1 or later installed:

pip3 install auto-gptq

If you have problems installing AutoGPTQ, please build from source instead:

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

Then try the following example code:

from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

model_name_or_path = "TheBloke/Llama2-22B-Daydreamer-v3-GPTQ"

use_triton = False

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

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        use_safetensors=True,
        trust_remote_code=False,
        device="cuda:0",
        use_triton=use_triton,
        quantize_config=None)

"""
# To download from a specific branch, use the revision parameter, as in this example:
# Note that `revision` requires AutoGPTQ 0.3.1 or later!

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        revision="gptq-4bit-32g-actorder_True",
        use_safetensors=True,
        trust_remote_code=False,
        device="cuda:0",
        quantize_config=None)
"""

prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
'''

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

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

# Inference can also be done using transformers' pipeline

# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

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

Compatibility

The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.

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

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!

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: Ajan Kanaga, David Ziegler, Raymond Fosdick, SuperWojo, Sam, webtim, Steven Wood, knownsqashed, Tony Hughes, Junyu Yang, J, Olakabola, Dan Guido, Stephen Murray, John Villwock, vamX, William Sang, Sean Connelly, LangChain4j, Olusegun Samson, Fen Risland, Derek Yates, Karl Bernard, transmissions 11, Trenton Dambrowitz, Pieter, Preetika Verma, Swaroop Kallakuri, Andrey, Slarti, Jonathan Leane, Michael Levine, Kalila, Joseph William Delisle, Rishabh Srivastava, Deo Leter, Luke Pendergrass, Spencer Kim, Geoffrey Montalvo, Thomas Belote, Jeffrey Morgan, Mandus, ya boyyy, Matthew Berman, Magnesian, Ai Maven, senxiiz, Alps Aficionado, Luke @flexchar, Raven Klaugh, Imad Khwaja, Gabriel Puliatti, Johann-Peter Hartmann, usrbinkat, Spiking Neurons AB, Artur Olbinski, chris gileta, danny, Willem Michiel, WelcomeToTheClub, Deep Realms, alfie_i, Dave, Leonard Tan, NimbleBox.ai, Randy H, Daniel P. Andersen, Pyrater, Will Dee, Elle, Space Cruiser, Gabriel Tamborski, Asp the Wyvern, Illia Dulskyi, Nikolai Manek, Sid, Brandon Frisco, Nathan LeClaire, Edmond Seymore, Enrico Ros, Pedro Madruga, Eugene Pentland, John Detwiler, Mano Prime, Stanislav Ovsiannikov, Alex, Vitor Caleffi, K, biorpg, Michael Davis, Lone Striker, Pierre Kircher, theTransient, Fred von Graf, Sebastain Graf, Vadim, Iucharbius, Clay Pascal, Chadd, Mesiah Bishop, terasurfer, Rainer Wilmers, Alexandros Triantafyllidis, Stefan Sabev, Talal Aujan, Cory Kujawski, Viktor Bowallius, subjectnull, ReadyPlayerEmma, zynix

Thank you to all my generous patrons and donaters!

Original model card: Nick Perez's Llama2 22B Daydreamer2 v3

Continuation of https://huggingface.co/nkpz/llama2-22b-daydreamer-v2

Gave it an epoch of https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1-mpt which it had never seen before - it had only seen Airoboros 2.0. I excluded all coding rows from this dataset - a dedicated model is better for that imo. I wanted it to focus on answering well in English.

I thought this was pretty good improvement. Its ability to roleplay and imitate speech styles was enhanced and I feel like it's still sharpening up its problem solving skills.

Its output style is right where I want it - dry and accurate enough when it's being asked for information, but has a lot character when it's answering fun prompts.

For input, it's flexible. It understands the Alpaca format well, but has been trained to handle a variety of input styles at this point.

I don't know what's next. I think I need to start benchmarking so I can more formally identify its weak points.

Examples edited with additional newlines to make it easier to read here.

Example 1: Q&A

Question: What is happening to the newspaper industry? Respond in a pirate accent.
Answer:
 The newspaper industry is being plundered by scurvy dogs and buccaneers like ye!
They're pillagin' yer booty with their fancy digital devices, like smartphones and tablets,
which make it easier for them to read online content instead of buyin' printed copies from us.
And don't forget about those pesky social media sites that are spreading rumors faster than the
winds on a galleon! So it's all hands on deck as we fight back against these scoundrels, or else
we'll be walkin' the plank soon enough! Avast ye landlubbers!

Example 2: Alpaca Instruction

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Angrily explain why pizza shouldn't be made with bad tomatoes.

### Response:

Listen, I know you think it's funny to make pizza with those rotten tomatoes, but let me tell you something -
bad tomatoes are not only disgusting and unhealthy, they also ruin the flavor of your pizza! You want a
delicious pie with fresh, juicy tomatoes that burst in your mouth, right?
Well, then, stop using those nasty tomatoes and stick to good quality ingredients for a truly satisfying pizza experience!
Trust me, once you try it, you won't go back! So please, don't even bother wasting your time making pizza with bad tomatoes
anymore; it's just not worth it. It makes me angry just thinking about it!

Example 3: Chat / Roleplay

You are speaking to Andre The Giant.
You: Hey, you're that wrestler guy, right?
Andre The Giant: Yes, I am indeed Andre the Giant. How can I help you?
You: So, how tall are you really? Like, what's your height in feet and inches?
Andre The Giant: Well, let's see... I stand at 7 ft 4 in (229 cm) tall.
You: Wow! That's so tall! And how much do you weigh?
Andre The Giant: I weigh around 500 lbs (227 kg). It's quite heavy, isn't it?
You: Yeah, I guess so. You must be strong too, considering your size.
Andre The Giant: Thank you for saying that. Strength is definitely important when dealing with my profession.
You: What made you decide to become a professional wrestler?
Andre The Giant: Well, I grew up watching wrestling on television, and I always admired the athleticism
and showmanship involved. When I got older, I decided to pursue it myself.
You: That's cool. Do you have any advice for aspiring wrestlers out there?
Andre The Giant: Absolutely! Always stay dedicated and focused, train hard, and never give up on yourself
or your dreams. Remember, anything is possible if you believe in yourself.