Facico/Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca
This project helps anyone who needs to develop a Chinese-language AI assistant or chatbot without access to massive computing power. It allows you to train a powerful LLaMA-based model to understand and respond to instructions in Chinese, even on a single consumer-grade graphics card. The output is a customized conversational AI model tailored to specific tasks or industries, making it usable by businesses, researchers, or developers in China.
4,136 stars. No commits in the last 6 months.
Use this if you need to build a specialized Chinese AI chatbot for tasks like customer service, legal advice, or medical Q&A, and you have limited GPU resources.
Not ideal if you primarily need a large language model for English-only tasks or if you have access to extensive, enterprise-level computing infrastructure.
Stars
4,136
Forks
410
Language
C
License
Apache-2.0
Category
Last pushed
Apr 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Facico/Chinese-Vicuna"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline....
lyogavin/airllm
AirLLM 70B inference with single 4GB GPU
GradientHQ/parallax
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
CrazyBoyM/llama3-Chinese-chat
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
CLUEbenchmark/CLUE
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained...