Facico/Chinese-Vicuna
A Chinese instruction-following LLaMA-based model fine-tuned with LoRA for low-resource training on consumer GPUs.
Not currently ranked — collecting fresh signals.
star history
This project provides methods to build and share Chinese instruction-following models based on LLaMA using LoRA parameter-efficient fine-tuning. It enables training Llama-7B instruction models on a single RTX-2080Ti (11GB) and multi-round chatbots with 2048 context length on an RTX-3090. The approach aims for high parameter efficiency, GPU friendliness, and easy deployment while following the Alpaca/Vicuna development paradigm.
Frequently asked
- What is Facico/Chinese-Vicuna?
- A Chinese instruction-following LLaMA-based model fine-tuned with LoRA for low-resource training on consumer GPUs.
- Is Chinese-Vicuna open source?
- Yes — Facico/Chinese-Vicuna is open source, released under the Apache-2.0 license.
- What language is Chinese-Vicuna written in?
- Facico/Chinese-Vicuna is primarily written in C.
- How popular is Chinese-Vicuna?
- Facico/Chinese-Vicuna has 4.1k stars on GitHub.
- Where can I find Chinese-Vicuna?
- Facico/Chinese-Vicuna is on GitHub at https://github.com/Facico/Chinese-Vicuna.