W = U_high * S_high * V_high^T + U_low * S_low * V_low^T

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import OSFConfig, get_peft_model

# Load base model
model = AutoModelForCausalLM.from_pretrained("facebook/opt-125m")

# Configure OSF
config = OSFConfig(
    target_modules=["q_proj", "v_proj"],  # Target attention layers
    effective_rank=8,                     # Default rank for decomposition
    rank_pattern={"q_proj": 16}           # Override rank for specific modules
)

# Apply OSF
model = get_peft_model(model, config)

# Train as usual
optimizer = torch.optim.AdamW(model.parameters(), lr=3e-4)

tokenizer = AutoTokenizer.from_pretrained("facebook/opt-125m")

inputs = tokenizer("Hello world", return_tensors="pt", padding=True)
loss = model(**inputs, labels=inputs.input_ids).loss
loss.backward()
optimizer.step()
optimizer.zero_grad()

# Specific module names
config = OSFConfig(target_modules=["q_proj", "k_proj", "v_proj", "o_proj"])

# All linear layers
config = OSFConfig(target_modules="all-linear")

# Model-specific defaults (automatically detected)
config = OSFConfig()  # Uses model-appropriate defaults

# Global preserved rank (applies to all target modules)
config = OSFConfig(effective_rank=16)  # preserves top-16 singular directions; trains the rest

# Automatic preserved rank (50% of the smaller matrix dimension per target)
config = OSFConfig(effective_rank=None)

# Per-module preserved-rank overrides
config = OSFConfig(
    effective_rank=8,
    rank_pattern={
        "q_proj": 16,      # Higher rank for query projection
        "gate_proj": 4     # Lower rank for gate projection
    }
)

# Fractional preserved rank is supported (interpreted per-target as fraction * min_dim)
config = OSFConfig(effective_rank=0.8)  # preserve 80% of min_dim; train remaining 20%
config = OSFConfig(rank_pattern={"q_proj": 0.5})  # preserve 50% on q_proj, others use global/default

# Task 1: train on domain A with initial preserved subspace
r = 8  # initial effective rank to preserve
model = get_peft_model(base_model, OSFConfig(effective_rank=r))
train_task(model, task_1_data)

# Task 2: recompute SVD on updated weights and increase preserved subspace
base_model = model.unload()  # unwrap base model without assuming internals
r += 4  # grow preserved subspace to include Task 1 knowledge
model = get_peft_model(base_model, OSFConfig(effective_rank=r))
train_task(model, task_2_data)

# Task 3: recompute again and expand preserved subspace further
base_model = model.unload()
r += 4
model = get_peft_model(base_model, OSFConfig(effective_rank=r))
train_task(model, task_3_data)

# Example: 4-task sequence with progressive budget allocation
n_tasks = 4
max_preserved_rank = 512  # Upper bound for preserved rank per target (heuristic)

for task_id in range(n_tasks):
    # Freeze increases over time; trainable capacity shrinks
    preserved_fraction = (task_id + 1) / n_tasks
    preserved_rank = int(max_preserved_rank * preserved_fraction)

    config = OSFConfig(
        target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
        effective_rank=preserved_rank,
    )

    print(
        f"Task {task_id + 1}: Preserving rank {preserved_rank} "
        f"({preserved_fraction:.1%} of max_preserved_rank - {max_preserved_rank} frozen); trainable rank = min_dim - preserved_rank"
    )

    model = get_peft_model(base_model, config)
    train_task(model, task_data[task_id])

# Memory usage remains close to base model
print(f"Base model parameters: {base_model.num_parameters():,}")
print(f"OSF model parameters: {osf_model.num_parameters():,}")  # Similar count

config = OSFConfig(
    target_modules=["dense", "intermediate.dense"],  # Custom layer names
    effective_rank=12,
    rank_pattern={"dense": 8, "intermediate.dense": 16}
)

# Use with gradient checkpointing for memory efficiency
model.gradient_checkpointing_enable()

# Apply weight decay selectively (regularizes low-rank factors to limit drift/overfitting in continual updates; keep small)
optimizer = torch.optim.AdamW([
    {"params": [p for n, p in model.named_parameters() if "U_low" in n], "weight_decay": 0.01},
    {"params": [p for n, p in model.named_parameters() if "S_low" in n], "weight_decay": 0.001},
    {"params": [p for n, p in model.named_parameters() if "V_low" in n], "weight_decay": 0.01},
], lr=1e-4)