RedHatAI / granite-3.1-2b-instruct-quantized.w4a16

python quantize.py --model_path ibm-granite/granite-3.1-2b-instruct --quant_path "output_dir/granite-3.1-2b-instruct-quantized.w4a16" --calib_size 1024 --dampening_frac 0.01 --observer mse --group_size 64

from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot, apply
import argparse
from compressed_tensors.quantization import QuantizationScheme, QuantizationArgs, QuantizationType, QuantizationStrategy


parser = argparse.ArgumentParser()
parser.add_argument('--model_path', type=str)
parser.add_argument('--quant_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('--group_size', type=int, default="128")
args = parser.parse_args()

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


NUM_CALIBRATION_SAMPLES = args.calib_size
DATASET_ID = "neuralmagic/LLM_compression_calibration"
DATASET_SPLIT = "train"
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))

def preprocess(example):
    return {"text": example["text"]}

ds = ds.map(preprocess)

def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        truncation=False,
        add_special_tokens=True,
    )


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

recipe = [
    GPTQModifier(
        targets=["Linear"],
        ignore=["lm_head"],
        scheme="w4a16",
        dampening_frac=args.dampening_frac,
        observer=args.observer,
        group_size=args.group_size
    )
]
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    num_calibration_samples=args.calib_size,
    max_seq_length=8196,
)

# Save to disk compressed.
model.save_pretrained(quant_path, save_compressed=True)
tokenizer.save_pretrained(quant_path)

OpenLLM Leaderboard V1:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/granite-3.1-2b-instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks openllm \
  --write_out \
  --batch_size auto \
  --output_path output_dir \
  --show_config

OpenLLM Leaderboard V2:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/granite-3.1-2b-instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks leaderboard \
  --write_out \
  --batch_size auto \
  --output_path output_dir \
  --show_config

HumanEval

Generation

python3 codegen/generate.py \
  --model neuralmagic/granite-3.1-2b-instruct-quantized.w4a16 \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

Sanitization

python3 evalplus/sanitize.py \
  humaneval/neuralmagic--granite-3.1-2b-instruct-quantized.w4a16_vllm_temp_0.2

Evaluation

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/neuralmagic--granite-3.1-2b-instruct-quantized.w4a16_vllm_temp_0.2-sanitized

guidellm --model neuralmagic/granite-3.1-2b-instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_server