from transformers import AutoProcessor, LlavaForConditionalGeneration

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

MODEL_ID = "llama-joycaption-beta-one-hf-llava"

# Load model.
model_class = LlavaForConditionalGeneration
model = model_class.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto")
processor = AutoProcessor.from_pretrained(MODEL_ID)

# Configure the quantization algorithm and scheme.
# In this case, we:
#   * quantize the weights to fp8 with per channel via ptq
#   * quantize the activations to fp8 with dynamic per token
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=["re:.*lm_head", "re:.*multi_modal_projector.*", "re:.*vision_tower.*"],
)

# Apply quantization and save to disk in compressed-tensors format.
SAVE_DIR = MODEL_ID + "-FP8-Dynamic"
oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR, save_compressed=True)
processor.save_pretrained(SAVE_DIR)