mirror of
https://github.com/NVIDIA/dgx-spark-playbooks.git
synced 2026-04-23 02:23:53 +00:00
90 lines
3.5 KiB
Python
90 lines
3.5 KiB
Python
#
|
|
# SPDX-FileCopyrightText: Copyright (c) 1993-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from unsloth import FastLanguageModel, FastModel
|
|
import torch
|
|
from trl import SFTTrainer, SFTConfig
|
|
from datasets import load_dataset
|
|
max_seq_length = 2048 # Supports RoPE Scaling internally, so choose any!
|
|
# Get LAION dataset
|
|
url = "https://huggingface.co/datasets/laion/OIG/resolve/main/unified_chip2.jsonl"
|
|
dataset = load_dataset("json", data_files = {"train" : url}, split = "train")
|
|
|
|
# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
|
|
fourbit_models = [
|
|
"unsloth/Meta-Llama-3.1-8B-bnb-4bit", # Llama-3.1 2x faster
|
|
"unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
|
|
"unsloth/Meta-Llama-3.1-70B-bnb-4bit",
|
|
"unsloth/Meta-Llama-3.1-405B-bnb-4bit", # 4bit for 405b!
|
|
"unsloth/Mistral-Small-Instruct-2409", # Mistral 22b 2x faster!
|
|
"unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
|
|
"unsloth/Phi-3.5-mini-instruct", # Phi-3.5 2x faster!
|
|
"unsloth/Phi-3-medium-4k-instruct",
|
|
"unsloth/gemma-2-9b-bnb-4bit",
|
|
"unsloth/gemma-2-27b-bnb-4bit", # Gemma 2x faster!
|
|
|
|
"unsloth/Llama-3.2-1B-bnb-4bit", # NEW! Llama 3.2 models
|
|
"unsloth/Llama-3.2-1B-Instruct-bnb-4bit",
|
|
"unsloth/Llama-3.2-3B-bnb-4bit",
|
|
"unsloth/Llama-3.2-3B-Instruct-bnb-4bit",
|
|
|
|
"unsloth/Llama-3.3-70B-Instruct-bnb-4bit" # NEW! Llama 3.3 70B!
|
|
] # More models at https://huggingface.co/unsloth
|
|
|
|
model, tokenizer = FastModel.from_pretrained(
|
|
model_name = "unsloth/gemma-3-4B-it",
|
|
max_seq_length = 2048, # Choose any for long context!
|
|
load_in_4bit = True, # 4 bit quantization to reduce memory
|
|
load_in_8bit = False, # [NEW!] A bit more accurate, uses 2x memory
|
|
full_finetuning = False, # [NEW!] We have full finetuning now!
|
|
# token = "hf_...", # use one if using gated models
|
|
)
|
|
|
|
# Do model patching and add fast LoRA weights
|
|
model = FastLanguageModel.get_peft_model(
|
|
model,
|
|
r = 16,
|
|
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
|
|
"gate_proj", "up_proj", "down_proj",],
|
|
lora_alpha = 16,
|
|
lora_dropout = 0, # Supports any, but = 0 is optimized
|
|
bias = "none", # Supports any, but = "none" is optimized
|
|
# [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
|
|
use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
|
|
random_state = 3407,
|
|
max_seq_length = max_seq_length,
|
|
use_rslora = False, # We support rank stabilized LoRA
|
|
loftq_config = None, # And LoftQ
|
|
)
|
|
|
|
trainer = SFTTrainer(
|
|
model = model,
|
|
train_dataset = dataset,
|
|
tokenizer = tokenizer,
|
|
args = SFTConfig(
|
|
max_seq_length = max_seq_length,
|
|
per_device_train_batch_size = 2,
|
|
gradient_accumulation_steps = 4,
|
|
warmup_steps = 10,
|
|
max_steps = 60,
|
|
logging_steps = 1,
|
|
output_dir = "outputs",
|
|
optim = "adamw_8bit",
|
|
seed = 3407,
|
|
),
|
|
)
|
|
trainer.train() |