llm-action
LLM knowledge base
Sharing technical knowledge and practical experience on large language models
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
12k stars
99 watching
1k forks
Language: HTML
last commit: almost 2 years agollmllm-inferencellm-servingllm-trainingllmops
Related projects:
| Repository | Description | Stars |
|---|---|---|
 paddlepaddle/paddlenlp | A comprehensive NLP and LLM library that provides an easy-to-use interface for a wide range of tasks, including text classification, neural search, question answering, information extraction, and more. | 12,224 |
 tloen/alpaca-lora | Tuning a large language model on consumer hardware using low-rank adaptation | 18,710 |
 facico/chinese-vicuna | An instruction-following Chinese LLaMA-based model project aimed at training and fine-tuning models on specific hardware configurations for efficient deployment. | 4,152 |
 cvi-szu/linly | A collection of pre-trained language models for Chinese text processing and dialogue generation. | 3,034 |
 ymcui/chinese-llama-alpaca | Develops and deploys large language models for natural language processing tasks in Chinese, particularly for text encoding and decoding. | 18,513 |
 openbmb/minicpm | A language model designed to surpass the capabilities of GPT-3.5-Turbo on various tasks such as text generation, tool calling, and long-text processing | 7,209 |
 lc1332/chinese-alpaca-lora | Develops and maintains a Chinese language model finetuned on LLaMA, used for text generation and summarization tasks. | 711 |
 phoebussi/alpaca-cot | Provides a unified interface for fine-tuning large language models with parameter-efficient methods and instruction collection data | 2,640 |
 hiyouga/llama-factory | A tool for efficiently fine-tuning large language models across multiple architectures and methods. | 36,219 |
 baichuan-inc/baichuan-7b | Develops a large-scale pretraining language model with state-of-the-art performance on various benchmarks for natural language understanding and generation tasks. | 5,680 |
 jittor/jittorllms | A high-performance deep learning framework designed to efficiently deploy large models on low-end hardware. | 2,389 |
 shm007g/llama-cult-and-more | Provides insights and practical guides for building and using large language models. | 427 |
 pengxiao-song/lawgpt | Develops a Chinese language-based large language model trained on legal knowledge to improve understanding and execution of laws | 5,868 |
 antimatter15/alpaca.cpp | A locally run Instruction-Tuned Chat-Style LLM project that combines foundation models and fine-tuning to create a chat interface. | 10,249 |
 git-cloner/llama2-lora-fine-tuning | Fine-tuning the LLaMA 2 chat model using DeepSpeed and Lora for improved performance on a large dataset. | 171 |