pyproject.toml

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "flowertune-nlp"
version = "1.0.0"
description = ""
license = "Apache-2.0"
dependencies = [
    "flwr[simulation]>=1.13.0",
    "flwr-datasets>=0.3.0",
    "torch==2.5.1",
    "trl==0.8.1",
    "bitsandbytes==0.45.0",
    "scipy==1.13.0",
    "peft==0.14.0",
    "transformers @ git+ssh://git@github.com/NX-AI/transformers.git@f99443e2c8bc2e929218c68d37ae96b4e0a11bd7",
    "sentencepiece==0.2.0",
    "omegaconf==2.3.0",
    "hf_transfer==0.1.8",
    "scikit-learn==1.6.0",
    "mlstm_kernels==1.0.3",
    "xlstm==2.0.1",
]

[tool.hatch.build.targets.wheel]
packages = ["."]

[tool.hatch.metadata]
allow-direct-references = true

[tool.flwr.app]
publisher = "mrs83"

[tool.flwr.app.components]
serverapp = "flowertune_nlp.server_app:app"
clientapp = "flowertune_nlp.client_app:app"

[tool.flwr.app.config]
model.name = "NX-AI/xLSTM-7b"
model.quantization = 4
model.gradient-checkpointing = true
model.lora.peft-lora-r = 16
model.lora.peft-lora-alpha = 128
train.save-every-round = 5
train.learning-rate-max = 5e-5
train.learning-rate-min = 1e-6
train.seq-length = 512
train.training-arguments.output-dir = ""
train.training-arguments.learning-rate = ""
train.training-arguments.per-device-train-batch-size = 8
train.training-arguments.gradient-accumulation-steps = 1
train.training-arguments.logging-steps = 1
train.training-arguments.num-train-epochs = 3
train.training-arguments.max-steps = 5
train.training-arguments.save-steps = 1000
train.training-arguments.save-total-limit = 10
train.training-arguments.max-grad-norm = 1.0
train.training-arguments.gradient-checkpointing = true
train.training-arguments.bf16 = true
train.training-arguments.tf32 = true
train.training-arguments.lr-scheduler-type = "constant"
strategy.fraction-fit = 0.25
strategy.fraction-evaluate = 0.0
num-server-rounds = 100

[tool.flwr.app.config.static]
dataset.name = "vicgalle/alpaca-gpt4"

[tool.flwr.federations]
default = "local-simulation"

[tool.flwr.federations.local-simulation]
options.num-supernodes = 20
options.backend.client-resources.num-cpus = 6
options.backend.client-resources.num-gpus = 1.0