Downloads · 30 days
0
154teru/llm-jp-3-13b-it15a4_fullset2048_lora
llm-jp-3-13b-it15a4_fullset2048_lora is a machine learning model from 154teru. 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.
- Developed by: 154teru - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
0
Access
Public
Updated Dec 17, 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.
LLM-JP-3-13Bモデルを使用し、 GoogleColaboratoryで推論を行うためのテンプレート。 Unslothを使用。
開発方針はSFTを中心として、datasetを人間の目と感性で 可能な限り一貫性を持たせた。 同時にパラメータを調整し、サンプルコードからmax_seq_length = 2048に変更。
pip install unsloth
pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install -U torch
pip install -U peft
必要なライブラリは適宜保存してください。
from unsloth import FastLanguageModel
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re
HF_TOKEN = "your_token_here"
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "154teru/llm-jp-3-13b-it15a4_fullset_lora"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=None,
load_in_4bit=True,
trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter_id, token=HF_TOKEN)
{
"task_id": "タスクID",
"input": "入力テキスト"
}
FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
input = dt["input"]
prompt = f"""以下は、タスクを説明する指示です。要求を適切に満たす回答を書きなさい。### 指示\n{input}\n### 回答\n"""
# 推論処理
json_file_id = re.sub(".*/", "", adapter_id)
with open("/content/submit.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
JSONLファイルとして保存
{
"task_id": "タスクID",
"input": "入力テキスト",
"output": "モデルの出力"
}
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "154teru/llm-jp-3-13b-it15a4_fullset2048_lora"
#huggingface TOKEN
HF_TOKEN = ""
dtype = None
load_in_4bit = True
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
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 = ""
FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
input = dt["input"]
prompt = f"""以下は、タスクを説明する指示です。要求を適切に満たす回答を書きなさい。### 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("/content/submit.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')