hiroshij/llm-jp-3-13b-finetune-joga-20231124

Uploaded model

• Developed by: hiroshij
• License: apache-2.0
• Finetuned from model : llm-jp/llm-jp-3-13b

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

How to finetune llm-jp/llm-jp-3-13b

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig from unsloth import FastLanguageModel import torch max_seq_length = 512
dtype = None load_in_4bit = True

model_id = "llm-jp/llm-jp-3-13b" new_model_id = "llm-jp-3-13b-finetune-joga-20231124"

model, tokenizer = FastLanguageModel.from_pretrained( model_name=model_id, dtype=dtype, load_in_4bit=load_in_4bit, trust_remote_code=True, )

model = FastLanguageModel.get_peft_model( model, r = 32, target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj",], lora_alpha = 32, lora_dropout = 0.05, bias = "none", use_gradient_checkpointing = "unsloth", random_state = 3407, use_rslora = False, loftq_config = None, max_seq_length = max_seq_length, )

HF_TOKEN = "Put-Your-TOKEN-here"

from datasets import load_dataset

dataset = load_dataset("json", data_files="/content/ichikara-instruction-003-001-1.json")

prompt = """### 指示 {}

回答

{}"""

""" formatting_prompts_func """ EOS_TOKEN = tokenizer.eos_token def formatting_prompts_func(examples): input = examples["text"] output = examples["output"] text = prompt.format(input, output) + EOS_TOKEN return { "formatted_text" : text, } pass

dataset = dataset.map( formatting_prompts_func, num_proc= 4, )

dataset

from trl import SFTTrainer from transformers import TrainingArguments from unsloth import is_bfloat16_supported

trainer = SFTTrainer( model = model, tokenizer = tokenizer, train_dataset=dataset["train"], max_seq_length = max_seq_length, dataset_text_field="formatted_text", packing = False, args = TrainingArguments( per_device_train_batch_size = 2, gradient_accumulation_steps = 4, num_train_epochs = 1, logging_steps = 10, warmup_steps = 10, save_steps=100, save_total_limit=2, max_steps=-1, learning_rate = 2e-4, fp16 = not is_bfloat16_supported(), bf16 = is_bfloat16_supported(), group_by_length=True, seed = 3407, output_dir = "outputs", report_to = "none", ), )

trainer_stats = trainer.train()