DeepSeek 系列工作解读、扩展和复现。

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

Scalable Python DS & ML, in an API compatible & lightning fast way.

The open-source repo for docs.dify.ai

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.

Integrate the DeepSeek API into popular softwares

Multimodal Chatbot based on Gradio

A framework for few-shot evaluation of language models.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.

DSPy: The framework for programming—not prompting—language models

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Javascript library for creating annotations in PDF documents

LOMO: LOw-Memory Optimization

AirLLM 70B inference with single 4GB GPU

leaked prompts of GPTs

Windows compile of bitsandbytes for use in text-generation-webui.

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Official repository for LongChat and LongEval

Ongoing research training transformer language models at scale, including: BERT & GPT-2

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

The Memory layer for AI Agents