Pixtral 12b Quantized.w8a8

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 TraceableLlavaForConditionalGeneration

# Load model.
model_id = mgoin/pixtral-12b
model = TraceableLlavaForConditionalGeneration.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 {
        "input_ids": torch.LongTensor(batch[0]["input_ids"]),
        "attention_mask": torch.tensor(batch[0]["attention_mask"]),
        "pixel_values": torch.tensor(batch[0]["pixel_values"]),
    }


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

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

# 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,
    output_dir=SAVE_DIR
)

视觉任务

• 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>

基于文本的任务

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 \

HumanEval

生成

python3 codegen/generate.py \
  --model neuralmagic/pixtral-12b-quantized.w8a8 \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

清理

python3 evalplus/sanitize.py \
  humaneval/neuralmagic/pixtral-12b-quantized.w8a8_vllm_temp_0.2

评估

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/neuralmagic/pixtral-12b-quantized.w8a8_vllm_temp_0.2-sanitized