Quantization

Quantization represents data with fewer bits, making it a useful technique for reducing memory-usage and accelerating inference especially when it comes to large language models (LLMs). There are several ways to quantize a model including:

• optimizing which model weights are quantized with the AWQ algorithm
• independently quantizing each row of a weight matrix with the GPTQ algorithm
• quantizing to 8-bit and 4-bit precision with the bitsandbytes library
• quantizing to as low as 2-bit precision with the AQLM algorithm

However, after a model is quantized it isn’t typically further trained for downstream tasks because training can be unstable due to the lower precision of the weights and activations. But since PEFT methods only add extra trainable parameters, this allows you to train a quantized model with a PEFT adapter on top! Combining quantization with PEFT can be a good strategy for training even the largest models on a single GPU. For example, QLoRA is a method that quantizes a model to 4-bits and then trains it with LoRA. This method allows you to finetune a 65B parameter model on a single 48GB GPU!

In this guide, you’ll see how to quantize a model to 4-bits and train it with LoRA.

Quantize a model

bitsandbytes is a quantization library with a Transformers integration. With this integration, you can quantize a model to 8 or 4-bits and enable many other options by configuring the BitsAndBytesConfig class. For example, you can:

• set load_in_4bit=True to quantize the model to 4-bits when you load it
• set bnb_4bit_quant_type="nf4" to use a special 4-bit data type for weights initialized from a normal distribution
• set bnb_4bit_use_double_quant=True to use a nested quantization scheme to quantize the already quantized weights
• set bnb_4bit_compute_dtype=torch.bfloat16 to use bfloat16 for faster computation

import torch
from transformers import BitsAndBytesConfig

config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
)

Pass the config to the from_pretrained method.

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", quantization_config=config)

Next, you should call the prepare_model_for_kbit_training() function to preprocess the quantized model for traininng.

from peft import prepare_model_for_kbit_training

model = prepare_model_for_kbit_training(model)

Now that the quantized model is ready, let’s set up a configuration.

LoraConfig

Create a LoraConfig with the following parameters (or choose your own):

from peft import LoraConfig

config = LoraConfig(
    r=16,
    lora_alpha=8,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
    lora_dropout=0.05
    bias="none",
    task_type="CAUSAL_LM"
)

Then use the get_peft_model() function to create a PeftModel from the quantized model and configuration.

from peft import get_peft_model

model = get_peft_model(model, config)

You’re all set for training with whichever training method you prefer!

LoftQ initialization

LoftQ initializes LoRA weights such that the quantization error is minimized, and it can improve performance when training quantized models. To get started, create a LoftQConfig and set loftq_bits=4 for 4-bit quantization.

from transformers import AutoModelForCausalLM
from peft import LoftQConfig, LoraConfig, get_peft_model

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", device_map="auto")
loftq_config = LoftQConfig(loftq_bits=4)

Now pass the loftq_config to the LoraConfig to enable LoftQ initialization, and create a PeftModel for training.

lora_config = LoraConfig(
    init_lora_weights="loftq",
    loftq_config=loftq_config,
    r=16,
    lora_alpha=8,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM"
)

model = get_peft_model(model, lora_config)

QLoRA-style training

QLoRA adds trainable weights to all the linear layers in the transformer architecture. Since the attribute names for these linear layers can vary across architectures, set target_modules to "all-linear" to add LoRA to all the linear layers:

config = LoraConfig(target_modules="all-linear", ...)

AQLM quantizaion

Additive Quantization of Language Models (AQLM) is a Large Language Models compression method. It quantizes multiple weights together and takes advantage of interdependencies between them. AQLM represents groups of 8-16 weights as a sum of multiple vector codes. This allows it to compress models down to as low as 2-bit with considerably low accuracy losses.

Since the AQLM quantization process is computationally expensive, a use of prequantized models is recommended. A partial list of available models can be found in the official aqlm repository.

The models support LoRA adapter tuning. To tune the quantized model you’ll need to install the aqlm inference library: pip install aqlm>=1.0.2. Finetuned LoRA adapters shall be saved separately, as merging them with AQLM quantized weights is not possible.

quantized_model = AutoModelForCausalLM.from_pretrained(
    "BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch",
    torch_dtype="auto", device_map="auto", low_cpu_mem_usage=True,
)

peft_config = LoraConfig(...)

quantized_model = get_peft_model(quantized_model, peft_config)

You can refer to the Google Colab example for an overview of AQLM+LoRA finetuning.

Next steps

If you’re interested in learning more about quantization, the following may be helpful:

• Learn more about details about QLoRA and check out some benchmarks on its impact in the Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA blog post.
• Read more about different quantization schemes in the Transformers Quantization guide.