zake7749 / Kyara
Lightweight and Effective Chinese LLM.
☆22Updated last month
Alternatives and similar repositories for Kyara:
Users that are interested in Kyara are comparing it to the libraries listed below
- A Traditional-Chinese instruction-following model with datasets based on Alpaca.☆136Updated 2 years ago
- ROUGE score calculator with traditional chinese word segmentation☆9Updated 3 years ago
- Official github repo for TMMLU+, Large scale traditional chinese massive multitask language understanding☆45Updated 8 months ago
- Generative Fusion Decoding (GFD) is a novel framework for integrating Large Language Models (LLMs) into multi-modal text recognition syst…☆79Updated 7 months ago
- finetune llama2 with traditional chinese dataset☆38Updated last year
- A distributed training framework for large language models powered by Lightning.☆19Updated last month
- A publishing website of a table collecting meta-learning-related papers in the area of human language processing.☆17Updated 3 years ago
- 🍳 NLPrep - dataset tool for many natural language processing task☆28Updated 3 years ago
- Official code for the ACL 2024 paper: Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New …☆47Updated 10 months ago
- Code for preprint "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆36Updated 3 weeks ago
- ⚙️Tool for NLP - handle file and text☆15Updated 2 months ago
- Toward Multi Modality Language Model - implementation of GPT-4o/Project Astra☆14Updated 4 months ago
- 🏃 hosting nlp models in one line☆20Updated 11 months ago
- Finetune LLaMA-7B with Chinese instruction datasets☆136Updated last year
- Transformers for Cantonese☆56Updated 4 years ago
- ☆10Updated 2 months ago
- ☆23Updated 6 months ago
- Revolutionize your development workflow with AI-powered code assistance, automating mock tests, suggestions, and unit test generation in …☆34Updated last month
- ☆45Updated this week
- ☆14Updated 3 years ago
- Code for "A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies."☆28Updated 3 years ago
- 聯發創新基地(MediaTek Research) 致力於研究基礎模型。我們將研究體現在適合繁體中文使用者的模型上,並在使用權許可的情況下,提供模型給學術界研究或產業界使用。☆225Updated last month
- We systematically studied the influencing factors when LLM generates benchmarks,By using our code, you can generate high-quality QA datas…☆16Updated last month
- 使用繁體中文資料集做的 Embedding 模型評測☆45Updated 9 months ago
- ☆53Updated this week
- Taiwanese Translation with BERT based model and RNN. Collection of Taiwanese text corpus☆11Updated 2 years ago
- CKIP CoreNLP Toolkits☆120Updated 2 years ago
- 🧑🏻🏫 NLP tutorials for newbies☆9Updated last year
- Transitioning from Open-Domain Chit-Chat to Task-Oriented Dialogues☆41Updated 2 years ago
- Benchmarking Complex Instruction-Following with Multiple Constraints Composition (NeurIPS 2024 Datasets and Benchmarks Track)☆76Updated 2 months ago