Downloads · 30 days
0
Hikaru94/llm-jp-3-13b-it
llm-jp-3-13b-it is a machine learning model from Hikaru94. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: Hikaru94 - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
0
Access
Public
Updated Nov 26, 2024
Repo size
501 MB
Likes
0
Public
Click a slice to open those files.
.safetensors501 MB · 99%
From the Hugging Face model README
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
'''python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig from unsloth import FastLanguageModel import torch max_seq_length = 512 # unslothではRoPEをサポートしているのでコンテキスト長は自由に設定可能 dtype = None # Noneにしておけば自動で設定 load_in_4bit = True # 今回は8Bクラスのモデルを扱うためTrue
model_id = "llm-jp/llm-jp-3-13b" new_model_id = "llm-jp-3-13b-it" #Fine-Tuningしたモデルにつけたい名前、it: Instruction Tuning
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 = "your_token" #@param {type:"string"}
from datasets import load_dataset
dataset = load_dataset("json", data_files="/content/ichikara-instruction-003-001-1.json")
from google.colab import drive drive.mount('/content/drive')
prompt = """### 指示 {}
{}"""
""" formatting_prompts_func: 各データをプロンプトに合わせた形式に合わせる """ EOS_TOKEN = tokenizer.eos_token # トークナイザーのEOSトークン(文末トークン) def formatting_prompts_func(examples): input = examples["text"] # 入力データ output = examples["output"] # 出力データ text = prompt.format(input, output) + EOS_TOKEN # プロンプトの作成 return { "formatted_text" : text, } # 新しいフィールド "formatted_text" を返す pass
dataset = dataset.map( formatting_prompts_func, num_proc= 4, # 並列処理数を指定 )
dataset
print(dataset["train"]["formatted_text"][3])
""" training_arguments: 学習の設定
output_dir: -トレーニング後のモデルを保存するディレクトリ
per_device_train_batch_size:
per_device_eval_batch_size:
gradient_accumulation_steps:
optim:
num_train_epochs:
eval_strategy:
eval_steps:
logging_strategy:
logging_steps:
warmup_steps:
save_steps:
save_total_limit:
max_steps:
learning_rate:
fp16:
bf16:
group_by_length:
report_to:
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", ), )
#@title 現在のメモリ使用量を表示 gpu_stats = torch.cuda.get_device_properties(0) start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3) max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3) print(f"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.") print(f"{start_gpu_memory} GB of memory reserved.")
#@title 学習実行 trainer_stats = trainer.train()
import json datasets = [] with open("/content/elyza-tasks-100-TV_0.jsonl", "r") as f: item = "" for line in f: line = line.strip() item += line if item.endswith("}"): datasets.append(json.loads(item)) item = ""
from tqdm import tqdm
FastLanguageModel.for_inference(model)
results = [] for dt in tqdm(datasets): input = dt["input"]
prompt = f"""### 指示\n{input}\n### 回答\n"""
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2) prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')
from google.colab import files
files.download(f"{new_model_id}_output.jsonl")
model.push_to_hub_merged( new_model_id, tokenizer=tokenizer, save_method="lora", token="your_token", private=True )
'''