Devstral-Small-2507-quantized.w4a16

vllm serve RedHatAI/Devstral-Small-2507-quantized.w4a16 --tensor-parallel-size 1 --tokenizer_mode mistral

python quantize.py --model_path mistralai/Devstral-Small-2507 --calib_size 1024 --dampening_frac 0.1 --observer mse --sym false --actorder weight

import argparse
import os
from datasets import load_dataset
from transformers import AutoModelForCausalLM
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from compressed_tensors.quantization import QuantizationScheme, QuantizationArgs, QuantizationType, QuantizationStrategy
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.protocol.instruct.messages import (
    SystemMessage, UserMessage
)

def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = os.path.join(repo_id, filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    return system_prompt

def parse_actorder(value):
    if value.lower() == "false":
        return False
    elif value.lower() == "weight":
        return "weight"
    elif value.lower() == "group":
        return "group"
    else:
        raise argparse.ArgumentTypeError("Invalid value for --actorder.")

def parse_sym(value):
    if value.lower() == "false":
        return False
    elif value.lower() == "true":
        return True
    else:
        raise argparse.ArgumentTypeError(f"Invalid value for --sym. Use false or true, but got {value}")


parser = argparse.ArgumentParser()
parser.add_argument('--model_path', type=str)
parser.add_argument('--calib_size', type=int, default=256)
parser.add_argument('--dampening_frac', type=float, default=0.1)
parser.add_argument('--observer', type=str, default="minmax")
parser.add_argument('--sym', type=parse_sym, default=True)
parser.add_argument(
    '--actorder',
    type=parse_actorder,
    default=False,
    help="Specify actorder as 'group' (string) or False (boolean)."
)
args = parser.parse_args()


model = AutoModelForCausalLM.from_pretrained(
    args.model_path,
    device_map="auto",
    torch_dtype="auto",
    use_cache=False,
    trust_remote_code=True,
)

ds = load_dataset("garage-bAInd/Open-Platypus", split="train")
ds = ds.shuffle(seed=42).select(range(args.calib_size))

SYSTEM_PROMPT = load_system_prompt(args.model_path, "SYSTEM_PROMPT.txt")
tokenizer = MistralTokenizer.from_hf_hub("mistralai/Devstral-Small-2507")

def tokenize(sample):
    tmp = tokenizer.encode_chat_completion(
        ChatCompletionRequest(
            messages=[
                SystemMessage(content=SYSTEM_PROMPT),
                UserMessage(content=sample['instruction']),
            ],
        )
    )
    return {'input_ids': tmp.tokens}

ds = ds.map(tokenize, remove_columns=ds.column_names)

quant_scheme = QuantizationScheme(
    targets=["Linear"],
    weights=QuantizationArgs(
        num_bits=4,
        type=QuantizationType.INT,
        symmetric=args.sym,
        group_size=128,
        strategy=QuantizationStrategy.GROUP,
        observer=args.observer,
        actorder=args.actorder
    ),
    input_activations=None,
    output_activations=None,
)

recipe = [
    GPTQModifier(
        targets=["Linear"],
        ignore=["lm_head"],
        dampening_frac=args.dampening_frac,
        config_groups={"group_0": quant_scheme},
    )
]

oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    num_calibration_samples=args.calib_size,
    max_seq_length=8192,
)

save_path = args.model_path + "-quantized.w4a16"
model.save_pretrained(save_path)

evalplus.evaluate --model "RedHatAI/Devstral-Small-2507-quantized.w4a16" \
                  --dataset [humaneval|mbpp] \
                  --base-url http://localhost:8000/v1 \
                  --backend openai --greedy