metadata
license: apache-2.0
Creation script
import torch
from datasets import load_dataset
from transformers import AutoTokenizer
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
from llmcompressor.transformers.compression.helpers import (
calculate_offload_device_map,
custom_offload_device_map,
)
recipe = """
quant_stage:
quant_modifiers:
QuantizationModifier:
ignore: ["lm_head"]
config_groups:
group_0:
weights:
num_bits: 8
type: float
strategy: tensor
dynamic: false
symmetric: true
input_activations:
num_bits: 8
type: float
strategy: tensor
dynamic: false
symmetric: true
targets: ["Linear"]
"""
model_stub = "teknium/OpenHermes-2.5-Mistral-7B"
model_name = model_stub.split("/")[-1]
device_map = calculate_offload_device_map(
model_stub, reserve_for_hessians=False, num_gpus=1, torch_dtype="auto"
)
model = SparseAutoModelForCausalLM.from_pretrained(
model_stub, torch_dtype="auto", device_map=device_map
)
tokenizer = AutoTokenizer.from_pretrained(model_stub)
output_dir = f"./{model_name}-FP8"
DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 4096
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
def preprocess(example):
return {
"text": tokenizer.apply_chat_template(
example["messages"],
tokenize=False,
)
}
ds = ds.map(preprocess)
def tokenize(sample):
return tokenizer(
sample["text"],
padding=False,
max_length=MAX_SEQUENCE_LENGTH,
truncation=True,
add_special_tokens=False,
)
ds = ds.map(tokenize, remove_columns=ds.column_names)
oneshot(
model=model,
output_dir=output_dir,
dataset=ds,
recipe=recipe,
max_seq_length=MAX_SEQUENCE_LENGTH,
num_calibration_samples=NUM_CALIBRATION_SAMPLES,
save_compressed=True,
)