CVI-SZU/Linly resource

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

3044 stars · 222 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Linly is a project releasing Chinese-adapted open large language models, including Chinese-LLaMA 1&2, Chinese-Falcon, Linly-OpenLLaMA base models, and the Linly-ChatFlow dialogue model, along with Chinese pretraining and instruction-tuning datasets. It provides reproducible training, evaluation, and quantized inference pipelines for Chinese LLMs.

Use cases

• download a Chinese LLaMA or Falcon base model for further fine-tuning
• deploy a Chinese chatbot model locally with quantization
• get Chinese instruction-tuning datasets for LLM training
• continue pretraining an English LLM on Chinese corpora
• run a Chinese conversational model on edge devices with llama.cpp
• evaluate Chinese LLM performance on benchmarks like C-Eval

When to choose

• you need open Chinese base or chat models with reproducible training code
• you want Chinese pretraining and instruction datasets for your own LLM work
• you need quantized Chinese LLM inference on CUDA or edge devices

When to avoid

• you need a hosted API service rather than self-hosted model weights
• you require a permissive license for all models (some weights are GPL v3)
• you need actively maintained cutting-edge models, as releases stopped in 2024

Facets

learning-resource · maturity maintenance

llm-training llm-inference nlp chatbot rag large-language-models machine-learning chatbots python chinese-nlp llama falcon openllama instruction-tuning pretraining-corpus quantization chatflow model-weights natural-language-processing gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="CVI-SZU/Linly")