alora

library0.3.0pypypi✓ verified 80d ago

Activated LoRA (aLoRA) is a low rank adapter architecture that allows reusing existing base model KV cache, built on top of PEFT. Version 0.3.0 is current; pre-1.0 release cadence is intermittent.

ai-ml llm-agents

pip install alora

github ↗package ↗

INSTALL

IMPORT

SIG · ALORA

alora

ai-mlpythonv0.3.0

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

AloraConfig

✓ import alora

✗ from alora import AloraConfig

Instantiate aLoraConfig, wrap a base model with AloraModel, and generate text.

from transformers import AutoModelForCausalLM, AutoTokenizer from alora import AloraConfig, AloraModel model_name = "gpt2" model = AutoModelForCausalLM.from_pretrained(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name) alora_config = AloraConfig( r=8, lora_alpha=16, target_modules=["q_proj", "v_proj"], use_activated_lora=True ) model = AloraModel(model, alora_config) inputs = tokenizer("Hello, I'm", return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0]))

Debug

Known issues

breakingv0.3.0 changed base class from PEFT's LoraModel to PeftModel. Custom subclasses of AloraModel may break if they rely on LoraModel internals.

fix

Update any custom subclass to use PeftModel instead of LoraModel, or pin alora==0.2.0.

affects: 0.2.0 -> 0.3.0

deprecatedbitsandbytes import path changed in PEFT; direct bnb imports are deprecated. Alora uses peft.utils for bnb-related modules.

fix

Ensure bitsandbytes is installed and use from peft.import_utils import is_bnb_available instead of direct bnb imports.

affects: >=0.2.0

gotchaAloraModel expects a HuggingFace model as the first argument, not model id. Passing a string causes AttributeError.

fix

Always call with an instantiated model object: AloraModel(model, config), not AloraModel('model_name', config).

affects: all

Upgrade

Version history

0.3.0latest on PyPI · released Jun 9, 2025

Audit

Dependencies

peftrequiredaLoRA subclasses PEFT models and requires bitsandbytes integration

torchrequiredUnderlying tensor operations and model loading

bitsandbytesoptionalRequired for quantization support (bnb import from PEFT)

Agent activity

59 hits · last 30 days

node

OpenAI (training)

Amazon

Perplexity

Resources

githubhttps://github.com/IBM/activated-lora ↗

packagehttps://pypi.org/project/alora/ ↗