-
CSIE, National Central University
- Hsinchu
- https://www.cakeresume.com/s--4DFyjSKR6ZIg-Jb53rSlCw--/kmes50215
Lists (3)
Sort Name ascending (A-Z)
Stars
🌠 List of software (HW interfaces, libs, protocols, etc) specifically suitable for resource-constrained Embedded Systems (low-memory and low-power) like 8-bit, 16-bit and 32-bit microcontrollers.
Few Shot Text Classification with Large Language Models
Fine-tuning of Flan-5T LLM for text classification
Fine-Tuning Microsoft Phi-2 for financial news sentiment analysis improved accuracy from 0.349 to 0.872 and reduced training loss by 38%. Dataset: 4846 entries with "Neutral," "Positive," and "Nega…
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
LLM, Fine Tuning, Llama 2, Gemma, Mixtral, vLLM, LangChain, RAG, ChromaDB, FAISS
LLM Finetuning with peft
Pre-Training and Fine-Tuning transformer models using PyTorch and the Hugging Face Transformers library. Whether you're delving into pre-training with custom datasets or fine-tuning for specific cl…
FineTune LLMs in few lines of code (Text2Text, Text2Speech, Speech2Text)
Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM
Chinese Grammar Error and Spelling Error Correction System - 中文文法錯誤及錯別字校正系統
Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch
Grammar correct project based Tencent's paper(Sequence to Action)
FinGAT: A Financial Graph Attention Networkto Recommend Top-K Profitable Stocks
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Fetching confused chars, including same pronunciation, similar pronunciation and similar character pattern
prompt2model - Generate Deployable Models from Natural Language Instructions
The official code of ALLECS: A Lightweight Language Error Correction System
llama2 finetuning with deepspeed and lora
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型,实现了包括LLaMA,ChatGLM,BLOOM,GPT2,Seq2Seq,BART,T5,UDA等模型的训练和预测,开箱即用。
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
pycorrector is a toolkit for text error correction. 文本纠错,实现了Kenlm,T5,MacBERT,ChatGLM3,Qwen2.5等模型应用在纠错场景,开箱即用。