Skip to content

v0.10.0: Fine-tune larger QLoRA models with DeepSpeed and FSDP, layer replication, enhance DoRA
Compare
Choose a tag to compare
@BenjaminBossan BenjaminBossan released this 21 Mar 10:20
· 292 commits to main since this release
v0.10.0
8221246
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.

Highlights

image

Support for QLoRA with DeepSpeed ZeRO3 and FSDP

We added a couple of changes to allow QLoRA to work with DeepSpeed ZeRO3 and Fully Sharded Data Parallel (FSDP). For instance, this allows you to fine-tune a 70B Llama model on two GPUs with 24GB memory each. Besides the latest version of PEFT, this requires bitsandbytes>=0.43.0, accelerate>=0.28.0, transformers>4.38.2, trl>0.7.11. Check out our docs on DeepSpeed and FSDP with PEFT, as well as this blogpost from answer.ai, for more details.

Layer replication

First time contributor @siddartha-RE added support for layer replication with LoRA. This allows you to duplicate layers of a model and apply LoRA adapters to them. Since the base weights are shared, this costs only very little extra memory, but can lead to a nice improvement of model performance. Find out more in our docs.

Improving DoRA

Last release, we added the option to enable DoRA in PEFT by simply adding use_dora=True to your LoraConfig. However, this only worked for non-quantized linear layers. With this PEFT release, we now also support Conv2d layers, as well as linear layers quantized with bitsandbytes.

Mixed LoRA adapter batches

If you have a PEFT model with multiple LoRA adapters attached to it, it's now possible to apply different adapters (or, in fact, no adapter) on different samples in the same batch. To do this, pass a list of adapter names as an additional argument. For example, if you have a batch of three samples:

output = model(**inputs, adapter_names=["adapter1", "adapter2", "__base__"])`

Here, "adapter1" and "adapter2" should be the same name as your corresponding LoRA adapters and "__base__" is a special name that refers to the base model without any adapter. Find more details in our docs.

Without this feature, if you wanted to run inference with different LoRA adapters, you'd have to use single samples or try to group batches with the same adapter, then switch between adapters using set_adapter -- this is inefficient and inconvenient. Therefore, it is recommended to use this new, faster method from now on when encountering this scenario.

New LoftQ initialization function

We added an alternative way to initialize LoRA weights for a quantized model using the LoftQ method, which can be more convenient than the existing method. Right now, using LoftQ requires you to go through multiple steps as shown here. Furthermore, it's necessary to keep a separate copy of the quantized weights, as those are not identical to the quantized weights from the default model.

Using the new replace_lora_weights_loftq function, it's now possible to apply LoftQ initialization in a single step and without the need for extra copies of the weights. Check out the docs and this example notebook to see how it works. Right now, this method only supports 4bit quantization with bitsandbytes, and the model has to be stored in the safetensors format.

Deprecations

The function prepare_model_for_int8_training was deprecated for quite some time and is now removed completely. Use prepare_model_for_kbit_training instead.

What's Changed

Besides these highlights, we added many small improvements and fixed a couple of bugs. All these changes are listed below. As always, we thank all the awesome contributors who helped us improve PEFT.

New Contributors

Full Changelog: v0.9.0...v0.10.0

Contributors

BenjaminBossan, pacman100, and 9 other contributors
Assets 2
Loading