Update README.md

08764a0 verified 11 months ago

7.88 kB

metadata

tags:
  - w4a16
  - int4
  - vllm
license: apache-2.0
license_link: >-
  https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md
language:
  - en
base_model: ibm-granite/granite-3.1-8b-instruct
library_name: transformers

granite-3.1-8b-instruct-quantized.w4a16

Model Overview

Model Architecture: granite-3.1-8b-instruct
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: INT4
- Activation quantization: INT4
Release Date: 1/8/2025
Version: 1.0
Model Developers: Neural Magic

Quantized version of ibm-granite/granite-3.1-8b-instruct. It achieves an average score of xxxx on the OpenLLM benchmark (version 1), whereas the unquantized model achieves xxxx.

Model Optimizations

This model was obtained by quantizing the weights of ibm-granite/granite-3.1-8b-instruct to INT4 data type, ready for inference with vLLM >= 0.5.2. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within transformers blocks are quantized.

Deployment

Use with vLLM

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

max_model_len, tp_size = 4096, 1
model_name = "neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True)
sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])

messages_list = [
    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]

prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]

outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)

generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)

vLLM also supports OpenAI-compatible serving. See the documentation for more details.

Creation

This model was created with llm-compressor by running the code snippet below.

python quantize.py --model_path ibm-granite/granite-3.1-8b-instruct --quant_path "output_dir/granite-3.1-8b-instruct-quantized.w4a16" --calib_size 1024 --dampening_frac 0.01 --observer mse  --actorder dynamic

from datasets import load_dataset
from transformers import AutoTokenizer
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import SparseAutoModelForCausalLM, 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")
args = parser.parse_args()

model = SparseAutoModelForCausalLM.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):
    concat_txt = example["instruction"] + "\n" + example["output"]
    return {"text": concat_txt}

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,
        actoder=args.actorder,
    )
]
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    num_calibration_samples=args.calib_size,
    max_seq_length=8196,
)

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

Evaluation

The model was evaluated on OpenLLM Leaderboard V1 and on HumanEval, using the following commands:

OpenLLM Leaderboard V1:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic-ent/granite-3.1-8b-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

HumanEval

Generation

python3 codegen/generate.py \
  --model neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16 \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

Sanitization

python3 evalplus/sanitize.py \
  humaneval/neuralmagic-ent--granite-3.1-8b-instruct-quantized.w4a16_vllm_temp_0.2

Evaluation

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/neuralmagic-ent--granite-3.1-8b-instruct-quantized.w4a16_vllm_temp_0.2-sanitized

Accuracy

OpenLLM Leaderboard V1 evaluation scores

Metric	ibm-granite/granite-3.1-8b-instruct	neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16
ARC-Challenge (Acc-Norm, 25-shot)	66.81	66.98
GSM8K (Strict-Match, 5-shot)	64.52	68.08
HellaSwag (Acc-Norm, 10-shot)	84.18	83.30
MMLU (Acc, 5-shot)	65.52	63.96
TruthfulQA (MC2, 0-shot)	60.57	60.62
Winogrande (Acc, 5-shot)	80.19	78.61
Average Score	70.30	70.26
Recovery	100.00	99.94

HumanEval pass@1 scores

Metric	ibm-granite/granite-3.1-8b-instruct	neuralmagic-ent/granite-3.1-8b-instruct-quantized.w4a16
HumanEval Pass@1	71.00	70.90