zjunlp/KnowLM

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1386 stars · 132 forks observed · 2026-08-28

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

KnowLM is an open-source framework for building knowledgeable large language models, covering data processing, pre-training, fine-tuning, knowledge augmentation, and deployment. It also provides a model zoo with ready-to-use bilingual (Chinese/English) models such as ZhiXi, KnowLM-IE, OneKE, and OceanGPT.

Use cases

• pretrain and fine-tune large language models on custom data
• instruction-tune a llama model with lora or deepspeed
• extract structured information from text with an LLM
• build a bilingual Chinese-English chat model
• augment LLM responses with retrieval-based knowledge
• detect hallucinations in LLM outputs
• edit knowledge inside a fine-tuned language model

When to choose

• you need an end-to-end open-source pipeline for LLM pre-training and instruction tuning
• you want ready-made bilingual Chinese/English LLM checkpoints for information extraction
• you work in Python with GPU clusters and want DeepSpeed/LoRA support

When to avoid

• you only need to call an LLM API without training or fine-tuning
• you lack GPU resources for large model training or inference
• you need a production-grade commercial LLM with vendor support

Facets

framework · maturity active

llm-training machine-learning rag nlp sdk large-language-models machine-learning artificial-intelligence python llm instruction-tuning lora deepspeed bilingual information-extraction model-zoo knowledge-editing hallucination-detection pre-training natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zjunlp/KnowLM")