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.

AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.

It is supported by:

Text Generation Webui - using Loader: AutoAWQ
vLLM - version 0.2.2 or later for support for all model types.
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	VMware Open Instruct	8192	19.23 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/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity-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: CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity-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/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity-AWQ --quantization awq --dtype auto

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

For example:

python

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/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity-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/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity-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

python

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:

shell

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)

python

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_name_or_path = "TheBloke/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity-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: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: brucethemoose's CaPlatTessDolXaBoros Yi 34B 200K Dare Ties Highdensity

Dolphin-2.2-yi-34b-200k, Nous-Capybara-34B, Tess-M-v1.4, Airoboros-3_1-yi-34b-200k, PlatYi-34B-200K-Q, and Una-xaberius-34b-v1beta merged with a new, experimental implementation of "dare ties" via mergekit. See:

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

https://github.com/cg123/mergekit/tree/dare

This variant is merged with a "higher than recommended" density with with the following config, and the tokenizer from chargoddard's Yi-Llama:

models:
  - model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
    # no parameters necessary for base model
  - model: /home/alpha/Storage/Models/Raw/migtissera_Tess-34B-v1.4
    parameters:
      weight: 0.19
      density: 0.6
  - model: /home/alpha//Storage/Models/Raw/bhenrym14_airoboros-3_1-yi-34b-200k
    parameters:
      weight: 0.14
      density: 0.5
  - model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
    parameters:
      weight: 0.19
      density: 0.6
  - model: /home/alpha/Storage/Models/Raw/kyujinpy_PlatYi-34B-200K-Q
    parameters:
      weight: 0.14
      density: 0.5
  - model: /home/alpha/FastModels/ehartford_dolphin-2.2-yi-34b-200k
    parameters:
      weight: 0.19
      density: 0.6
  - model: /home/alpha/FastModels/fblgit_una-xaberius-34b-v1beta
    parameters:
      weight: 0.15
      density: 0.08
merge_method: dare_ties
base_model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
parameters:
  int8_mask: true
dtype: bfloat16

Testing Notes

Various densities were tested with perplexity tests and long context prompts. Relatively high densities seem to perform better, contrary to the findings of the Super Mario paper.

This particular version is merged with more than the "recommended" max density of 0.5. It seems to result in even better perplexity, but I'm not sure if this translates to better output.

Weights that add up to 1 seems to be optimal.

Dare Ties is also resulting in seemingly better, lower perplexity merges than a regular ties merge, task arithmetic or a slerp merge.

Xaberuis is not a 200K model, hence it was merged at a very low density to try and preserve Yi 200K's long context performance while still inheriting some of Xaberius's performance.

I chose not to include other finetunes because they aren't trained on the 200K base. If any other 200K finetunes pop up, let me know.

Prompt template: Orca-Vicuna?

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

It might recognize ChatML from Dolphin+Xaberius, and Llama-chat from Airoboros.

Sometimes the model "spells out" the stop token as </s> like Capybara, so you may need to add </s> as an additional stopping condition.

Running

Being a Yi model, try disabling the BOS token and/or running a lower temperature with 0.05-0.13 MinP, a little repitition penalty, and no other samplers. Yi tends to run "hot" by default.

24GB GPUs can run Yi-34B-200K models at 45K-75K context with exllamav2. I go into more detail in this post

I recommend exl2 quantizations profiled on data similar to the desired task. It is especially sensitive to the quantization data at low bpw!

To load this in full-context backends like transformers and vllm, you must change max_position_embeddings in config.json to a lower value than 200,000, otherwise you will OOM!

Credits:

https://github.com/cg123/mergekit/tree/dare

https://huggingface.co/ehartford/dolphin-2.2-yi-34b-200k

https://huggingface.co/kyujinpy/PlatYi-34B-200K-Q

https://huggingface.co/NousResearch/Nous-Capybara-34B/

https://huggingface.co/bhenrym14/airoboros-3_1-yi-34b-200k

https://huggingface.co/migtissera/Tess-M-v1.4

https://huggingface.co/fblgit/una-xaberius-34b-v1beta

https://huggingface.co/chargoddard/Yi-34B-200K-Llama

https://huggingface.co/01-ai/Yi-34B-200K