SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,738 results · Page 283 of 993

LLMsBook

AI developer platforms

LLMsBook is a practical code summary repository for the book "Large Language Model Practical Guide: Application Practice and Scenario Implementation," hosted on GitHub. The project organizes code by book chapters, covering tokenizer training, PEFT-based Llama fine-tuning, DPO-based preference alignment, DeepSeek Coder-based SQL fine-tuning, Baichuan-based role-playing model fine-tuning, Qwen-based dialogue element extraction model fine-tuning, BGE-based vector fine-tuning, ChatGLM3-based knowledge base answer generation task fine-tuning and Streamlit application building, as well as practical content such as building AutoGPT based on Langchain. The repository also records book errata and welcomes feedback via issues.

Read more

LLMStack

Other AI tools

LLMStack is a no-code platform for building generative AI applications, chatbots, and agents, with the ability to connect to your own data. It supports mainstream model providers such as OpenAI, Cohere, Stability AI, and Hugging Face, making it easy for users to build powerful applications with these models. The platform supports importing a variety of data sources, including web URLs, sitemaps, PDFs, audio, PPT, Google Drive, Notion, and more, and connects the data with LLM models to enhance generative AI applications and chatbots. Users can also collaborate on building applications: publicly share applications or restrict access through a fine-grained permissions model, and use viewer and collaborator roles to allow multiple people to jointly modify and build applications.

Read more

lmm-r1

AI developer platforms

LMM-R1 is a fork project of OpenRLHF, aimed at providing reinforcement learning training infrastructure for large multimodal models (LMMs) to enhance their multimodal reasoning capabilities. The project proposes a two-stage rule-based reinforcement learning framework: the first stage is Foundational Reasoning Enhancement (FRE), which uses pure text data to establish a strong reasoning foundation; the second stage is Multimodal Generalization Training (MGT), which extends reasoning capabilities to the multimodal domain. Through this framework, LMM-R1 can significantly improve the reasoning performance of 3B-scale multimodal models using limited training data. The project supports training algorithms such as PPO, REINFORCE++, and RLOO, supports models such as Qwen2.5-VL, Phi3.5-V, and Phi4-Multimodal, and provides complete training scripts and dataset format specifications.

Read more

localGPT

AI office

LocalGPT is a fully private local document intelligence platform that uses GPT models on a local device to converse with documents, with data never leaving the machine. It is based on retrieval-augmented generation (RAG) and combines capabilities such as hybrid search, reranking, and intelligent routing. It supports formats including PDF, DOCX, HTML, Markdown, and TXT, making it suitable for individuals and organizations that prioritize data privacy to perform document question answering, summarization, and insight analysis locally.

Read more