Gemma 3 4b It Quantized.w4a16

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from transformers import AutoProcessor, Gemma3ForConditionalGeneration
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot


# Load model.
model_id = "google/gemma-3-4b-it"
model = Gemma3ForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "neuralmagic/calibration"
DATASET_SPLIT = {"LLM": "train[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)

dampening_frac=0.05

def data_collator(batch):
    assert len(batch) == 1, "Only batch size of 1 is supported for calibration"
    item = batch[0]
    collated = {}
    import torch


    for key, value in item.items():
        if isinstance(value, torch.Tensor):
            collated[key] = value.unsqueeze(0)
        elif isinstance(value, list) and isinstance(value[0][0], int):
            # Handle tokenized inputs like input_ids, attention_mask
            collated[key] = torch.tensor(value)
        elif isinstance(value, list) and isinstance(value[0][0], float):
            # Handle possible float sequences
            collated[key] = torch.tensor(value)
        elif isinstance(value, list) and isinstance(value[0][0], torch.Tensor):
            # Handle batched image data (e.g., pixel_values as [C, H, W])
            collated[key] = torch.stack(value)  # -> [1, C, H, W]
        elif isinstance(value, torch.Tensor):
            collated[key] = value
        else:
            print(f"[WARN] Unrecognized type in collator for key={key}, type={type(value)}")
    
    return collated
   


# Recipe
recipe = [
    GPTQModifier(
        targets="Linear",
        ignore=["re:.*lm_head.*", "re:.*embed_tokens.*", "re:vision_tower.*", "re:multi_modal_projector.*"],
        sequential_update=True,
        sequential_targets=["Gemma3DecoderLayer"],
        dampening_frac=dampening_frac,
    )
]

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16"

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=data_collator,
    output_dir=SAVE_DIR
)

OpenLLM v1

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True,enforce_eager=True \
  --tasks openllm \
  --batch_size auto