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.
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 AWQ support.
If you try the vLLM examples below and get an error about quantization being unrecognised, or other AWQ-related issues, please install vLLM from Github source.
When using vLLM as a server, pass the --quantization awq parameter, for example:
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/speechless-codellama-34b-v2.0-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 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
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: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: Jiangwen Su's Speechless Codellama 34B v2.0
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
Model Developers Meta
Variations Code Llama comes in three model sizes, and three variants:
Code Llama: base models designed for general code synthesis and understanding
Code Llama - Python: designed specifically for Python
Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B and 34B parameters.
This repository contains the base version of the 13B parameters model.
Input Models input text only.
Output Models generate text only.
Model Architecture Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
Model Dates Code Llama and its variants have been trained between January 2023 and July 2023.
Status This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
Intended Use Cases Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
Out-of-Scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
Hardware and Software
Training Factors We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
Carbon Footprint In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
Training Data
All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the research paper for details).
Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
Ethical Considerations and Limitations
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
