Downloads · 30 days
0
fkmt/llm-jp-3-13b-finetune-f3
llm-jp-3-13b-finetune-f3 is a machine learning model from fkmt. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
llm-jp-3-13bをベースモデルとし,ichikara-instruction-003-001-1 と ichikara-instruction-003-002-1 (ただしID:ichikara-instruction-003-002-0003479-001を除いたデータ) を学習データとし,LoRAによるインストラクションチューニングを行った.
Downloads · 30 days
0
Access
Public
Updated Dec 25, 2024
Repo size
250 MB
Likes
0
Public
Click a slice to open those files.
.safetensors250 MB · 98%
From the Hugging Face model README
llm-jp-3-13bをベースモデルとし,ichikara-instruction-003-001-1 と ichikara-instruction-003-002-1 (ただしID:ichikara-instruction-003-002-0003479-001を除いたデータ) を学習データとし,LoRAによるインストラクションチューニングを行った.
Omnicampusでの実行を想定した利用方法を記す.
!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
from peft import PeftModel
import torch
from tqdm import tqdm
import json
HF_TOKEN = "Hugging Face Token" # 変更する
model_id = "models/models--llm-jp--llm-jp-3-13b/snapshots/cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a"
adapter_id = "fkmt/llm-jp-3-13b-finetune-f3"
# QLoRA config
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
# Load model
model = AutoModelForCausalLM.from_pretrained(
model_id,
quantization_config=bnb_config,
device_map="auto",
token = HF_TOKEN
)
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
# 元のモデルにLoRAのアダプタを統合。
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
input = "野球選手が今シーズン活躍するために取り組むべき5つのことを教えてください。"
prompt = f"""### 指示
{input}
### 回答
"""
tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
attention_mask = torch.ones_like(tokenized_input)
with torch.no_grad():
outputs = model.generate(
tokenized_input,
attention_mask=attention_mask,
max_new_tokens=100,
do_sample=False,
repetition_penalty=1.2,
pad_token_id=tokenizer.eos_token_id
)[0]
output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
print(output)