hppRC/llm-lora-classification
LLMとLoRAを用いたテキスト分類
This project explores how well large language models (LLMs) can classify Japanese text, similar to how BERT models are used. It takes Japanese text, like news articles, and categorizes it into predefined labels. Data scientists and machine learning engineers working with Japanese text classification would find this useful for understanding LLM performance.
No commits in the last 6 months.
Use this if you are a data scientist or machine learning engineer exploring high-performance text classification for Japanese content using modern large language models.
Not ideal if you need production-ready results without further fine-tuning and validation, as the experimental results are not guaranteed for accuracy due to single-run, non-cross-validated tests.
Stars
98
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jul 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/hppRC/llm-lora-classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jpmorganchase/llm-email-spam-detection
LLM for Email Spam Detection
makerlinck/AntLLM
A auto-classifier for files based on Langchain & Deepdanbooru-tagger-mini
Nightey3s/profanity-detection
A robust multimodal system for detecting and rephrasing profanity in both speech and text,...
byunsj/KoTox-Korean-Toxic-Instruction-Dataset
KoTox is an automatically generated instruction dataset in Korean. The instruction set is used...
JuanLara18/classifai
Classify any text dataset with one config file. OpenAI, Anthropic, or Ollama — guaranteed...