Instructions to use hirosan6595/llm-jp-3-13b-finetune-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hirosan6595/llm-jp-3-13b-finetune-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hirosan6595/llm-jp-3-13b-finetune-2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hirosan6595/llm-jp-3-13b-finetune-2") model = AutoModelForCausalLM.from_pretrained("hirosan6595/llm-jp-3-13b-finetune-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hirosan6595/llm-jp-3-13b-finetune-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hirosan6595/llm-jp-3-13b-finetune-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hirosan6595/llm-jp-3-13b-finetune-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hirosan6595/llm-jp-3-13b-finetune-2
- SGLang
How to use hirosan6595/llm-jp-3-13b-finetune-2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "hirosan6595/llm-jp-3-13b-finetune-2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hirosan6595/llm-jp-3-13b-finetune-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "hirosan6595/llm-jp-3-13b-finetune-2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hirosan6595/llm-jp-3-13b-finetune-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio
How to use hirosan6595/llm-jp-3-13b-finetune-2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hirosan6595/llm-jp-3-13b-finetune-2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hirosan6595/llm-jp-3-13b-finetune-2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for hirosan6595/llm-jp-3-13b-finetune-2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="hirosan6595/llm-jp-3-13b-finetune-2", max_seq_length=2048, ) - Docker Model Runner
How to use hirosan6595/llm-jp-3-13b-finetune-2 with Docker Model Runner:
docker model run hf.co/hirosan6595/llm-jp-3-13b-finetune-2
How to use from
Unsloth StudioInstall Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hirosan6595/llm-jp-3-13b-finetune-2 to start chattingUsing HuggingFace Spaces for Unsloth
# No setup required# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hirosan6595/llm-jp-3-13b-finetune-2 to start chattingLoad model with FastModel
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="hirosan6595/llm-jp-3-13b-finetune-2",
max_seq_length=2048,
)Quick Links
Uploaded model
- Developed by: HiroSan6595
- 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.
Sample Use
以下elyza-tasks-100-TV_0.jsonlの回答のためのコード
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install -U xformers --index-url https://download.pytorch.org/whl/cu124
!pip install --no-deps "trl<0.9.0" peft accelerate bitsandbytes
import torch
if torch.cuda.get_device_capability()[0] >= 8:
!pip install --no-deps packaging ninja einops "flash-attn>=2.6.3"
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-finetune-2" #Fine-Tuningしたモデルにつけたい名前
# FastLanguageModel インスタンスを作成
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
# SFT用のモデルを用意
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 = "mytoken"
"""
dataset: 学習に用いるデータセット
ベースコードでは以下のリンクからデータをダウンロードして使います。zipを展開(!unzip)してデータのパスを指定してください。
(https://liat-aip.sakura.ne.jp/wp/llmのための日本語インストラクションデータ作成/llmのための日本語インストラクションデータ-公開/)
関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎.
ichikara-instruction: LLMのための日本語インストラクションデータの構築. 言語処理学会第30回年次大会(2024)
omnicampusの開発環境では取得したデータを左側にドラッグアンドドロップしてお使いください。
"""
from datasets import load_dataset
dataset = load_dataset("json", data_files="./ichikara-instruction-003-001-1.json")
dataset
# 学習時のプロンプトフォーマットの定義
prompt = """### 指示
{}
### 回答
{}"""
"""
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
# # 各データにフォーマットを適用
dataset = dataset.map(
formatting_prompts_func,
num_proc= 4, # 並列処理数を指定
)
dataset
print(dataset["train"]["formatted_text"][3])
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,
eval_steps=0.2,
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",
),
)
trainer_stats = trainer.train()
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.")
trainer_stats = trainer.train()
model.push_to_hub_merged(
new_model_id,
tokenizer=tokenizer,
# save_method="lora",
token=HF_TOKEN,
private=True
)
- Downloads last month
- 7
Model tree for hirosan6595/llm-jp-3-13b-finetune-2
Base model
llm-jp/llm-jp-3-13b
Install Unsloth Studio (macOS, Linux, WSL)
# Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hirosan6595/llm-jp-3-13b-finetune-2 to start chatting