Hugging Face's logo

TheBloke
/
Llama2-22B-Daydreamer-v3-GGUF

Transformers
GGUF
llama
Model card Files Community
1
Llama2-22B-Daydreamer-v3-GGUF / README.md
TheBloke's picture
TheBloke
Upload README.md
85092e8
preview code
|
raw
history blame
19.6 kB
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
TheBlokeAI

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

Llama2 22B Daydreamer2 v3 - GGUF

Description

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

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.

The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.

Here are a list of clients and libraries that are known to support GGUF:

  • llama.cpp.
  • text-generation-webui, the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
  • KoboldCpp, now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
  • LM Studio, version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
  • LoLLMS Web UI, should now work, choose the c_transformers backend. A great web UI with many interesting features. Supports CUDA GPU acceleration.
  • ctransformers, now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
  • llama-cpp-python, supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
  • candle, added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

Prompt template: Alpaca 

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

### Instruction:
{prompt}

### Response:

Compatibility

These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9

They are now also compatible with many third party UIs and libraries - please see the list at the top of the 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
llama2-22b-daydreamer-v3.Q2_K.gguf Q2_K 2 9.08 GB 11.58 GB smallest, significant quality loss - not recommended for most purposes
llama2-22b-daydreamer-v3.Q3_K_S.gguf Q3_K_S 3 9.47 GB 11.97 GB very small, high quality loss
llama2-22b-daydreamer-v3.Q3_K_M.gguf Q3_K_M 3 10.61 GB 13.11 GB very small, high quality loss
llama2-22b-daydreamer-v3.Q3_K_L.gguf Q3_K_L 3 11.61 GB 14.11 GB small, substantial quality loss
llama2-22b-daydreamer-v3.Q4_0.gguf Q4_0 4 12.34 GB 14.84 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama2-22b-daydreamer-v3.Q4_K_S.gguf Q4_K_S 4 12.42 GB 14.92 GB small, greater quality loss
llama2-22b-daydreamer-v3.Q4_K_M.gguf Q4_K_M 4 13.18 GB 15.68 GB medium, balanced quality - recommended
llama2-22b-daydreamer-v3.Q5_0.gguf Q5_0 5 15.04 GB 17.54 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama2-22b-daydreamer-v3.Q5_K_S.gguf Q5_K_S 5 15.04 GB 17.54 GB large, low quality loss - recommended
llama2-22b-daydreamer-v3.Q5_K_M.gguf Q5_K_M 5 15.47 GB 17.97 GB large, very low quality loss - recommended
llama2-22b-daydreamer-v3.Q6_K.gguf Q6_K 6 17.91 GB 20.41 GB very large, extremely low quality loss
llama2-22b-daydreamer-v3.Q8_0.gguf Q8_0 8 23.19 GB 25.69 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.

Example llama.cpp command

Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.

For compatibility with older versions of llama.cpp, or for any third-party libraries or clients that haven't yet updated for GGUF, please use GGML files instead.

./main -t 10 -ngl 32 -m llama2-22b-daydreamer-v3.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nWrite a story about llamas\n\n### Response:"

Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8. If offloading all layers to GPU, set -t 1.

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

Change -c 4096 to the desired sequence length for this model. 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 from Python using ctransformers

First install the package 

# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers

Simple example code to load one of these GGUF models 

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/Llama2-22B-Daydreamer-v3-GGUF", model_file="llama2-22b-daydreamer-v3.q4_K_M.gguf", model_type="llama", gpu_layers=50)

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

How to use with LangChain

Here's guides on using llama-cpp-python or ctransformers with LangChain:

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.

Special thanks to: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

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

What is it? Llama 2 13b expanded to the size of a Llama 1 33b model in certain areas, with the empty surrounding space filled with llama 33b data. (Base Model: https://huggingface.co/chargoddard/llama2-22b-blocktriangular) This is then finetuned on a 3090 by creating large loras and merging them. When I first started with 22b models, I looked for signs of knowledge transfer but didn't see it, so that's not a goal - the goal is just to throw lots of data at it until it adapts well to its surgically implanted parts. Datasets used are a mix of instruction, roleplay, and conversational data, often curated.

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.