GPU Timeline (Single GPU):
Chunk 1: [Config A] → [Config B] → [Config C] → [Config D]
Chunk 2: [Config A] → [Config B] → [Config C] → [Config D]
Chunk 3: [Config A] → [Config B] → [Config C] → [Config D]

pip install rapidfireai

# Authenticate with Hugging Face
hf auth login --token YOUR_TOKEN

# Workaround for current issue: https://github.com/huggingface/xet-core/issues/527
pip uninstall -y hf-xet

# Initialize RapidFire AI
rapidfireai init

# Start the RapidFire AI server
rapidfireai start

from rapidfireai import Experiment
from rapidfireai.automl import List, RFGridSearch, RFModelConfig, RFLoraConfig, RFSFTConfig
from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load dataset
dataset = load_dataset("bitext/Bitext-customer-support-llm-chatbot-training-dataset")
train_dataset = dataset["train"].select(range(128)).shuffle(seed=42)
eval_dataset = dataset["train"].select(range(100, 124)).shuffle(seed=42)

# Define data formatting function
def formatting_function(row):
    return {
        "prompt": [
            {"role": "system", "content": "You are a helpful customer support assistant."},
            {"role": "user", "content": row["instruction"]},
        ],
        "completion": [
            {"role": "assistant", "content": row["response"]}
        ]
    }

# Initialize experiment
experiment = Experiment(experiment_name="sft-customer-support")

# Define multiple LoRA configurations to compare
peft_configs = List([
    RFLoraConfig(r=8, lora_alpha=16, lora_dropout=0.1,
                 target_modules=["q_proj", "v_proj"], bias="none"),
    RFLoraConfig(r=32, lora_alpha=64, lora_dropout=0.1,
                 target_modules=["q_proj", "k_proj", "v_proj", "o_proj"], bias="none")
])

# Define multiple training configurations
# 2 base configs × 2 PEFT configs = 4 total training runs
config_set = List([
    RFModelConfig(
        model_name="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
        peft_config=peft_configs,
        training_args=RFSFTConfig(  # Wraps TRL's SFTConfig
            learning_rate=1e-3,
            per_device_train_batch_size=4,
            max_steps=128,
            fp16=True,
        ),
        model_type="causal_lm",
        model_kwargs={"device_map": "auto", "dtype": "auto", "use_cache": False},
        formatting_func=formatting_function,
    ),
    RFModelConfig(
        model_name="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
        peft_config=peft_configs,
        training_args=RFSFTConfig(
            learning_rate=1e-4,  # Different learning rate
            per_device_train_batch_size=4,
            max_steps=128,
            fp16=True,
        ),
        model_type="causal_lm",
        model_kwargs={"device_map": "auto", "dtype": "auto", "use_cache": False},
        formatting_func=formatting_function,
    )
])

# Define model creation function
def create_model(model_config):
    model = AutoModelForCausalLM.from_pretrained(
        model_config["model_name"],
        **model_config["model_kwargs"]
    )
    tokenizer = AutoTokenizer.from_pretrained(model_config["model_name"])
    return (model, tokenizer)

# Create grid search over all configurations
config_group = RFGridSearch(configs=config_set, trainer_type="SFT")

# Run all 4 configurations concurrently with chunk-based scheduling
experiment.run_fit(config_group, create_model, train_dataset, eval_dataset,
                   num_chunks=4, seed=42)

# End experiment
experiment.end()

from rapidfireai.automl import RFSFTConfig

training_args = RFSFTConfig(
    learning_rate=5e-5,
    per_device_train_batch_size=4,
    num_train_epochs=3,
    max_length = 512,
    # ... all other SFTConfig parameters supported
)

from rapidfireai.automl import RFDPOConfig

training_args = RFDPOConfig(
    beta=0.1,
    loss_type="sigmoid",
    max_length=1024,
    learning_rate=5e-4,
    # ... all other DPOConfig parameters supported
)

from rapidfireai.automl import RFGRPOConfig

training_args = RFGRPOConfig(
    learning_rate=5e-6,
    num_generations=8,
    max_completion_length=256,
    # ... all other GRPOConfig parameters supported
)

GPU Timeline (Single GPU):
Chunk 1: [Config A] → [Config B] → [Config C] → [Config D]
Chunk 2: [Config A] → [Config B] → [Config C] → [Config D]
Chunk 3: [Config A] → [Config B] → [Config C] → [Config D]
...

# Grid search: tests all combinations
config_group = RFGridSearch(configs=config_list, trainer_type="SFT")

# Random search: samples N configurations
config_group = RFRandomSearch(configs=config_list, trainer_type="DPO", num_samples=10)

from rapidfireai.automl import RFLoraConfig
from peft import TaskType

lora_config = RFLoraConfig(
    task_type=TaskType.CAUSAL_LM,
    r=64,
    lora_alpha=64,
    lora_dropout=0.1,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
    bias="none"
)

def correctness_reward(prompts, completions, answer, **kwargs):
    """Reward for correct answers"""
    responses = [completion[0]['content'] for completion in completions]
    extracted = [extract_answer(r) for r in responses]
    return [2.0 if r == a else 0.0 for r, a in zip(extracted, answer)]

def format_reward(completions, **kwargs):
    """Reward for proper formatting"""
    import re
    pattern = r"<reasoning>.*?</reasoning>\s*<answer>.*?</answer>"
    responses = [completion[0]["content"] for completion in completions]
    matches = [re.match(pattern, r) for r in responses]
    return [0.5 if match else 0.0 for match in matches]

# Use in model config
config = RFModelConfig(
    reward_funcs=[correctness_reward, format_reward],
    # ... other parameters
)

from rapidfireai.automl import RFModelConfig, RFSFTConfig, RFLoraConfig

model_config = RFModelConfig(
    model_name="meta-llama/Llama-3.1-8B-Instruct",
    peft_config=RFLoraConfig(
        r=16, lora_alpha=32, lora_dropout=0.05,
        target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
        bias="none",
    ),
    training_args=RFSFTConfig(
        learning_rate=2e-4,
        per_device_train_batch_size=1,
        gradient_accumulation_steps=8,
        fsdp="full_shard auto_wrap",
        fsdp_config={
            "sharding_strategy": "FULL_SHARD",
            "auto_wrap_policy": "TRANSFORMER_BASED_WRAP",
            "backward_prefetch": "backward_pre",
            "forward_prefetch": True,
            "use_orig_params": False,
            "cpu_ram_efficient_loading": True,
            "offload_params": True,
            "sync_module_states": True,
            "limit_all_gathers": True,
        },
    ),
    model_type="causal_lm",
    model_kwargs={"dtype": "auto"},
)

# MLflow only (default on local installs)
rapidfireai start --tracking-backends mlflow

# TensorBoard only
rapidfireai start --tracking-backends tensorboard

# Any combination
rapidfireai start --tracking-backends mlflow tensorboard trackio

# Fewer chunks = less overhead, less frequent comparison
experiment.run_fit(..., num_chunks=2)

# More chunks = more overhead, more frequent comparison
experiment.run_fit(..., num_chunks=16)

from transformers import BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
)

model_kwargs = {
    "quantization_config": bnb_config,
    "device_map": "auto",
}