Meta-Llama-2-7B-quantized.FP4

Creation

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.utils import dispatch_for_generation

MODEL_ID = "meta-llama/Llama-2-7b-hf"

# Load model.
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")


DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"

NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
ds = ds.shuffle(seed=42)


def preprocess(example):
    return {
        "text": tokenizer.apply_chat_template(
            example["messages"],
            tokenize=False,
        )
    }


ds = ds.map(preprocess)


# Tokenize inputs.
def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
        add_special_tokens=False,
    )


ds = ds.map(tokenize, remove_columns=ds.column_names)

smoothing_strength = 0.5
recipe = [
    SmoothQuantModifier(smoothing_strength=smoothing_strength),
    QuantizationModifier(
        ignore=["re:.*lm_head.*"],
        config_groups={
            "group_0": {
                "targets": ["Linear"],
                "weights": {
                    "num_bits": 4,
                    "type": "float",
                    "strategy": "tensor_group",
                    "group_size": 16,
                    "symmetric": True,
                    "observer": "minmax",
                },
                "input_activations": {
                    "num_bits": 4,
                    "type": "float",
                    "strategy": "tensor_group",
                    "group_size": 16,
                    "symmetric": True,
                    "dynamic": "local",
                    "observer": "minmax",
                },
            }
        },
    ),
]

# Save to disk in compressed-tensors format.
SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-NVFP4"

# Apply quantization.
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    output_dir=SAVE_DIR,
)

model.save_pretrained(SAVE_DIR, save_compressed=True)
tokenizer.save_pretrained(SAVE_DIR)