poteminr/instruct-ner
Instruct LLMs for flat and nested NER. Fine-tuning Llama and Mistral models for instruction named entity recognition. (Instruction NER)
This project helps domain experts extract specific terms from text, even when those terms are complex or overlap. You provide raw text and define the types of entities you want to find (like 'Drugname' or 'Drugform'). The system then uses large language models to identify and categorize these terms, giving you a structured list of extracted entities from your input text. It's designed for professionals who need to automatically tag and organize information within specialized texts.
No commits in the last 6 months.
Use this if you need to accurately identify and extract specific, predefined entities from text, especially in specialized fields like medicine, where you can customize what to look for.
Not ideal if your entity definitions are extremely broad, or if you need to extract entities that are deeply embedded and overlapping within complex text structures, as performance may be limited for very intricate nested entities.
Stars
89
Forks
9
Language
Python
License
Apache-2.0
Category
Last pushed
May 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/poteminr/instruct-ner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training