Llama-3.2-11B-Vision-Instruct-quantized.w4a16

from transformers import AutoProcessor
from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
model_id = "neuralmagic/Llama-3.2-11B-Vision-Instruct-quantized.w4a16"
llm = LLM(
    model=model_id,
    max_model_len=4096,
    max_num_seqs=16,
    limit_mm_per_prompt={"image": 1},
)
processor = AutoProcessor.from_pretrained(model_id)


# prepare inputs
question = "What is the content of this image?"
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": f"{question}"},
        ],
    },
]
prompt = processor.apply_chat_template(
    messages, add_generation_prompt=True,tokenize=False
)
image = ImageAsset("cherry_blossom").pil_image.convert("RGB")
inputs = {
    "prompt": prompt,
    "multi_modal_data": {
        "image": image
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

import requests
import torch
from PIL import Image
from transformers import AutoProcessor

from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableMllamaForConditionalGeneration

# Load model.
model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
model = TraceableMllamaForConditionalGeneration.from_pretrained(
    model_id, device_map="auto", torch_dtype="auto"
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048


# 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="W4A16",
        ignore=["re:.*lm_head", "re:multi_modal_projector.*", "re:vision_model.*"],
    ),
]

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=DATASET_ID,
    splits=DATASET_SPLIT,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=data_collator,
)