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.
It is also now supported by continuous batching server vLLM, allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.
Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
You like to use emojis. You can speak fluently in many languages, for example: English, Chinese.
You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.
User: {prompt}
Assistant:
Licensing
The creator of the source model has listed its license as apache-2.0, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: OpenBuddy's OpenBuddy OpenLlama 7B v12.
Provided files, and AWQ parameters
For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
Note: at the time of writing, vLLM has not yet done a new release with support for the quantization parameter.
If you try the code below and get an error about quantization being unrecognised, please install vLLM from Github source.
When using vLLM from Python code, pass the quantization=awq parameter, for example:
python
1from vllm import LLM, SamplingParams
23prompts =[4"Hello, my name is",5"The president of the United States is",6"The capital of France is",7"The future of AI is",8]9sampling_params = SamplingParams(temperature=0.8, top_p=0.95)1011llm = LLM(model="TheBloke/openbuddy-openllama-7B-v12-bf16-AWQ", quantization="awq", dtype="half")1213outputs = llm.generate(prompts, sampling_params)1415# Print the outputs.16for output in outputs:17 prompt = output.prompt
18 generated_text = output.outputs[0].text
19print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
Serving this model from TGI
TGI merged support for AWQ on September 25th, 2023. At the time of writing you need to use the :latest Docker container: ghcr.io/huggingface/text-generation-inference:latest
1from awq import AutoAWQForCausalLM
2from transformers import AutoTokenizer
34model_name_or_path ="TheBloke/openbuddy-openllama-7B-v12-bf16-AWQ"56# Load model7model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,8 trust_remote_code=False, safetensors=True)9tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)1011prompt ="Tell me about AI"12prompt_template=f'''You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
13Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
14If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
15You like to use emojis. You can speak fluently in many languages, for example: English, Chinese.
16You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
17You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.
1819User: {prompt}20Assistant:
2122'''2324print("\n\n*** Generate:")2526tokens = tokenizer(27 prompt_template,28 return_tensors='pt'29).input_ids.cuda()3031# Generate output32generation_output = model.generate(33 tokens,34 do_sample=True,35 temperature=0.7,36 top_p=0.95,37 top_k=40,38 max_new_tokens=51239)4041print("Output: ", tokenizer.decode(generation_output[0]))4243"""
44# Inference should be possible with transformers pipeline as well in future
45# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
46from transformers import pipeline
4748print("*** Pipeline:")
49pipe = pipeline(
50 "text-generation",
51 model=model,
52 tokenizer=tokenizer,
53 max_new_tokens=512,
54 do_sample=True,
55 temperature=0.7,
56 top_p=0.95,
57 top_k=40,
58 repetition_penalty=1.1
59)
6061print(pipe(prompt_template)[0]['generated_text'])
62"""
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 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: OpenBuddy's OpenBuddy OpenLlama 7B v12
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
