from llmcompressor.modifiers.quantization import GPTQModifier  
from llmcompressor.transformers import oneshot  
from transformers import AutoModelForCausalLM, AutoTokenizer  

# 加载模型  
model_stub = "Qwen/Qwen3-32B"  
model_name = model_stub.split("/")[-1]  

num_samples = 1024  
max_seq_len = 8192  

model = AutoModelForCausalLM.from_pretrained(model_stub)  

tokenizer = AutoTokenizer.from_pretrained(model_stub)  

def preprocess_fn(example):  
  return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}  

ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")  
ds = ds.map(preprocess_fn)  

# 配置量化算法和方案  
recipe = GPTQModifier(  
    ignore=["lm_head"],  
    sequential_targets=["Qwen3DecoderLayer"],  
    targets="Linear",  
    scheme="W4A16",  
    dampening_frac=0.1,  
)  

# 应用量化  
oneshot(  
    model=model,  
    dataset=ds,   
    recipe=recipe,  
    max_seq_length=max_seq_len,  
    num_calibration_samples=num_samples,  
)  

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

lm-evaluation-harness

lm_eval \  
  --model vllm \  
  --model_args pretrained="RedHatAI/Qwen3-32B-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \  
  --tasks openllm \  
  --apply_chat_template\  
  --fewshot_as_multiturn \  
  --batch_size auto  

lm_eval \  
  --model vllm \  
  --model_args pretrained="RedHatAI/Qwen3-32B-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \  
  --tasks mgsm \  
  --apply_chat_template\  
  --batch_size auto  

lm_eval \  
  --model vllm \  
  --model_args pretrained="RedHatAI/Qwen3-32B-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=16384,enable_chunk_prefill=True,tensor_parallel_size=1 \  
  --tasks leaderboard \  
  --apply_chat_template\  
  --fewshot_as_multiturn \  
  --batch_size auto  

lighteval

lighteval_model_arguments.yaml

model_parameters:  
  model_name: RedHatAI/Qwen3-32B-quantized.w4a16  
  dtype: auto  
  gpu_memory_utilization: 0.9  
  max_model_length: 40960  
  generation_parameters:  
    temperature: 0.6  
    top_k: 20  
    min_p: 0.0  
    top_p: 0.95  
    max_new_tokens: 32768  

lighteval vllm \  
  --model_args lighteval_model_arguments.yaml \  
  --tasks lighteval|aime24|0|0 \  
  --use_chat_template = true  

lighteval vllm \  
  --model_args lighteval_model_arguments.yaml \  
  --tasks lighteval|aime25|0|0 \  
  --use_chat_template = true  

lighteval vllm \  
  --model_args lighteval_model_arguments.yaml \  
  --tasks lighteval|math_500|0|0 \  
  --use_chat_template = true  

lighteval vllm \  
  --model_args lighteval_model_arguments.yaml \  
  --tasks lighteval|gpqa:diamond|0|0 \  
  --use_chat_template = true  

lighteval vllm \  
  --model_args lighteval_model_arguments.yaml \  
  --tasks extended|lcb:codegeneration \  
  --use_chat_template = true