from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableMistral3ForConditionalGeneration
from datasets import load_dataset, interleave_datasets
from PIL import Image
import io

# 加载模型
model_stub = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
model_name = model_stub.split("/")[-1]

num_text_samples = 1024
num_vision_samples = 1024
max_seq_len = 8192

processor = AutoProcessor.from_pretrained(model_stub)

model = TraceableMistral3ForConditionalGeneration.from_pretrained(
    model_stub,
    device_map="auto",
    torch_dtype="auto",
)

# 纯文本数据子集
def preprocess_text(example):
    input = {
        "text": processor.apply_chat_template(
            example["messages"],
            add_generation_prompt=False,
        ),
        "images": None,
    }
    tokenized_input = processor(**input, max_length=max_seq_len, truncation=True)
    tokenized_input["pixel_values"] = tokenized_input.get("pixel_values", None)
    tokenized_input["image_sizes"] = tokenized_input.get("image_sizes", None)
    return tokenized_input

dst = load_dataset("neuralmagic/calibration", name="LLM", split="train").select(range(num_text_samples))
dst = dst.map(preprocess_text, remove_columns=dst.column_names)

# 文本+视觉数据子集
def preprocess_vision(example):
    messages = []
    image = None
    for message in example["messages"]:
        message_content = []
        for content in message["content"]:
            if content["type"] == "text":
                message_content.append({"type": "text", "text": content["text"]})
            else:
                message_content.append({"type": "image"})
                image = Image.open(io.BytesIO(content["image"]))

        messages.append(
            {
                "role": message["role"],
                "content": message_content,
            }
        )

    input = {
        "text": processor.apply_chat_template(
            messages,
            add_generation_prompt=False,
        ),
        "images": image,
    }
    tokenized_input = processor(**input, max_length=max_seq_len, truncation=True)
    tokenized_input["pixel_values"] = tokenized_input.get("pixel_values", None)
    tokenized_input["image_sizes"] = tokenized_input.get("image_sizes", None)
    return tokenized_input

dsv = load_dataset("neuralmagic/calibration", name="VLM", split="train").select(range(num_vision_samples))
dsv = dsv.map(preprocess_vision, remove_columns=dsv.column_names)

# 交错子集
ds = interleave_datasets((dsv, dst))

# 配置量化算法和方案
recipe = GPTQModifier(
    ignore=["language_model.lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
    sequential_targets=["MistralDecoderLayer"],
    dampening_frac=0.01,
    targets="Linear",
    scheme="W4A16",
)

# 定义数据整理器
def data_collator(batch):
    import torch
    assert len(batch) == 1
    collated = {}
    for k, v in batch[0].items():
        if v is None:
            continue
        if k == "input_ids":
            collated[k] = torch.LongTensor(v)
        elif k == "pixel_values":
            collated[k] = torch.tensor(v, dtype=torch.bfloat16)
        else:
            collated[k] = torch.tensor(v)
    return collated


# 应用量化
oneshot(
    model=model,
    dataset=ds, 
    recipe=recipe,
    max_seq_length=max_seq_len,
    data_collator=data_collator,
    num_calibration_samples=num_text_samples + num_vision_samples,
)

# 以compressed-tensors格式保存到磁盘
save_path = model_name + "-quantized.w4a16"
model.save_pretrained(save_path)
processor.save_pretrained(save_path)
print(f"模型和分词器保存至: {save_path}")

MMLU

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks mmlu \
  --num_fewshot 5 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

ARC挑战

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks arc_challenge \
  --num_fewshot 25 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

GSM8k

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.9,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks gsm8k \
  --num_fewshot 8 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

Hellaswag

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks hellaswag \
  --num_fewshot 10 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

Winogrande

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks winogrande \
  --num_fewshot 5 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

TruthfulQA

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks truthfulqa \
  --num_fewshot 0 \
  --apply_chat_template\
  --batch_size auto

MMLU-pro

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks mmlu_pro \
  --num_fewshot 5 \
  --apply_chat_template\
  --fewshot_as_multiturn \
  --batch_size auto

MMMU

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.9,max_images=8,enable_chunk_prefill=True,tensor_parallel_size=2 \
  --tasks mmmu_val