File size: 1,571 Bytes
97cc65c 43263be 97cc65c 43263be |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
import subprocess
import sys
from unsloth import FastLanguageModel
from trl import SFTTrainer
from transformers import TrainingArguments
from datasets import load_dataset
subprocess.check_call([sys.executable, "-m", "pip", "install", "-r", "requirements.txt"])
model, tokenizer = FastLanguageModel.from_pretrained(
"unsloth/gemma-2-2b-it",
max_seq_length = 2048,
load_in_4bit = True,
)
model = FastLanguageModel.get_peft_model(
model,
r = 64,
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
lora_alpha = 32,
lora_dropout = 0,
bias = "none",
use_gradient_checkpointing = "unsloth",
random_state = 3407,
)
dataset = load_dataset("json", data_files="python_security_dataset.json", split="train")
trainer = SFTTrainer(
model = model,
tokenizer = tokenizer,
train_dataset = dataset,
dataset_text_field = "messages",
max_seq_length = 2048,
args = TrainingArguments(
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4,
warmup_steps = 10,
max_steps = 300,
learning_rate = 2e-4,
fp16 = True,
logging_steps = 1,
output_dir = "k1ng_final",
optim = "adamw_8bit",
),
)
trainer.train()
model.save_pretrained("k1ng_by_alikay_h")
tokenizer.save_pretrained("k1ng_by_alikay_h")
# آپلود به HF
from huggingface_hub import notebook_login, HfApi
notebook_login()
api = HfApi()
api.upload_folder(folder_path="k1ng_by_alikay_h", repo_id="alikayh/k1ng-v1", repo_type="model") |