Downloads · 30 days
0
ykawahara/llm-jp-3-13b-finetune-1800
llm-jp-3-13b-finetune-1800 is a machine learning model from ykawahara. 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.
This model is a fine-tuned version of llm-jp-3-13b-finetune using lora and ichikara instructions.
Downloads · 30 days
0
Access
Public
Updated Dec 26, 2024
Repo size
250 MB
Likes
0
Public
Click a slice to open those files.
.safetensors250 MB · 98%
From the Hugging Face model README
This model is a fine-tuned version of llm-jp-3-13b-finetune using lora and ichikara instructions.
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
bitsandbytes の 4-bit 量子化を設定して読み込み。peft パッケージを使用して、LoRA (特に QLoRA) 形式で微調整されたモデルを読み込み。!python -m pip install --upgrade pip
!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
# Hugging Faceで取得したTokenをこちらに貼る。
HF_TOKEN = "<YOUR_HF_TOKEN>"
!python -m pip install --upgrade pip
!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
# Hugging Faceで取得したTokenをこちらに貼る。
HF_TOKEN = ""
adapter_id = "ykawahara/llm-jp-3-13b-finetuned-1800"
# 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, # 例: "meta-llama/Llama-2-13b-hf" など
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)
# LoRA アダプタの読み込み
model = PeftModel.from_pretrained(model, adapter_id, token=HF_TOKEN)
# データセットの読み込み
# omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
datasets = []
with open("./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 = ""
# gemma
results = []
for data in tqdm(datasets):
input = data["input"]
prompt = f"""### 指示
{input}
### 回答
"""
input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**input_ids,
max_new_tokens=512,
do_sample=False,
repetition_penalty=1.2,
)
output = tokenizer.decode(outputs[0][input_ids.input_ids.size(1):], skip_special_tokens=True)
results.append({"task_id": data["task_id"], "input": input, "output": output})
results = []
for data in tqdm(datasets):
input = data["input"]
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)
results.append({"task_id": data["task_id"], "input": input, "output": output})