RedHatAI / Qwen2.5-VL-7B-Instruct-quantized.w8a8

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import (
    TraceableQwen2_5_VLForConditionalGeneration,
)

# Load model.
model_id = "Qwen/Qwen2.5-VL-7B-Instruct"
model = TraceableQwen2_5_VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[: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=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Define a oneshot data collator for multimodal inputs.
def data_collator(batch):
    assert len(batch) == 1
    return {key: torch.tensor(value) for key, value in batch[0].items()}


# Recipe
recipe = [
    GPTQModifier(
        targets="Linear",
        scheme="W8A8",
        sequential_targets=["Qwen2_5_VLDecoderLayer"],
        ignore=["lm_head", "re:visual.*"],
    ),
]

SAVE_DIR==f"{model_id.split('/')[1]}-quantized.w8a8"

# 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
)

Vision Tasks

• vqav2
• docvqa
• mathvista
• mmmu
• chartqa

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Text-based Tasks

MMLU

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 \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

MGSM

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,max_model_len=4096,max_gen_toks=2048,max_num_seqs=128,tensor_parallel_size=<n>,gpu_memory_utilization=0.9 \
  --tasks mgsm_cot_native \
  --apply_chat_template \
  --num_fewshot 0 \
  --batch_size auto \
  --output_path output_dir