aitraining llm --train \
  --model meta-llama/Llama-3.2-1B \
  --data-path ./data.jsonl \
  --project-name lora-model \
  --peft \
  --lora-r 16 \
  --lora-alpha 32

from autotrain.trainers.clm.params import LLMTrainingParams
from autotrain.project import AutoTrainProject

params = LLMTrainingParams(
    model="meta-llama/Llama-3.2-1B",
    data_path="./data.jsonl",
    project_name="lora-model",

    trainer="sft",

    # LoRA configuration
    peft=True,
    lora_r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    target_modules="all-linear",  # Default: all-linear

    epochs=3,
    batch_size=4,
    lr=2e-4,  # Higher LR works with LoRA
)

project = AutoTrainProject(params=params, backend="local", process=True)
project.create()

# 标准缩放
lora_r=16
lora_alpha=32  # alpha/r = 2

# 更激进
lora_r=16
lora_alpha=64  # alpha/r = 4

# 保守
lora_r=16
lora_alpha=16  # alpha/r = 1

# All linear layers (default)
target_modules="all-linear"

# Attention layers only
target_modules="q_proj,k_proj,v_proj,o_proj"

# Include MLP
target_modules="q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj"

aitraining llm --train \
  --model meta-llama/Llama-3.2-8B \
  --data-path ./data.jsonl \
  --project-name quantized-lora \
  --peft \
  --quantization int4

params = LLMTrainingParams(
    model="meta-llama/Llama-3.2-8B",
    data_path="./data.jsonl",
    project_name="quantized-lora",

    peft=True,
    lora_r=16,
    quantization="int4",  # or "int8"
)

params = LLMTrainingParams(
    ...
    peft=True,
    # merge_adapter=True is the default
)

aitraining llm --train \
  --model meta-llama/Llama-3.2-1B \
  --data-path ./data.jsonl \
  --project-name lora-model \
  --peft \
  --no-merge-adapter

aitraining tools merge-llm-adapter \
  --base-model-path meta-llama/Llama-3.2-1B \
  --adapter-path ./lora-model \
  --output-folder ./merged-model

from peft import PeftModel
from transformers import AutoModelForCausalLM

# Load base model
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")

# Load and merge adapter
model = PeftModel.from_pretrained(model, "./lora-model")
model = model.merge_and_unload()

# Save merged model
model.save_pretrained("./merged-model")

aitraining tools convert_to_kohya \
  --adapter-path ./lora-model \
  --output-path ./kohya-lora.safetensors

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")

# Load adapter
model = PeftModel.from_pretrained(model, "./lora-model")

# Use for inference
inputs = tokenizer("Hello", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)