"""NVFP4A16 without a calibration dataset.

Playbook §3.16, measured 2026-09-08 on this architecture: with scheme NVFP4A16
llm-compressor logs `Inferred DataFreePipeline` and NEVER touches the dataset.
Passing one is therefore pure liability, and it cost two failures here:

  * llmcompressor demands a model PROCESSOR whenever a dataset is provided, which
    is what killed the v2 pass (`DogOnKeyboard` ships no processor_config.json).
  * building the calib set calls the fast tokenizer with truncation=True, which
    mutates the Rust backend in place and `save_pretrained` then BAKES that cap
    into the shipped tokenizer.json -- playbook §3.14, fatal on a newer
    transformers for a vision model.

Dropping the dataset removes both for zero loss, because the quant is data-free.
Everything else -- targets, ignore list, save path -- matches the reference script.
"""
import argparse, json, sys, importlib.util
spec = importlib.util.spec_from_file_location(
    "ref", "/tank/aimodels/meromero-v2-nvfp4-work/quant_nvfp4_gemma.py")
ref = importlib.util.module_from_spec(spec)
# The reference module runs argparse at IMPORT with required=True args, so an
# empty argv still exits 2. Feed placeholders; our own parse happens after.
_real_argv = sys.argv
sys.argv = ["ref", "--model", "/dev/null", "--calib", "/dev/null", "--out", "/dev/null"]
spec.loader.exec_module(ref)

sys.argv = _real_argv
ap = argparse.ArgumentParser()
ap.add_argument("--model", required=True)
ap.add_argument("--out", required=True)
ap.add_argument("--scheme", default="NVFP4A16")
a = ap.parse_args()

assert a.scheme.endswith("A16"), f"{a.scheme} is not weight-only; it needs calibration data"
print(f"loading {a.model}", flush=True)
model, tok = ref.load_model(a.model)

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
recipe = QuantizationModifier(targets="Linear", scheme=a.scheme, ignore=ref.IGNORE)
print(f"NVFP4 oneshot (DATA-FREE): scheme={a.scheme}, Linear-only, "
      f"vision/audio/projector/embed/lm_head/norms kept BF16", flush=True)
oneshot(model=model, recipe=recipe)

print(f"saving -> {a.out}", flush=True)
model.save_pretrained(a.out, save_compressed=True)
tok.save_pretrained(a.out)
print("DONE", flush=True)