A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

An Open Large Reasoning Model for Real-World Solutions

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

Using GPT to parse PDF

A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

A Slack Export archive viewer that allows you to easily view and share your Slack team's export

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Easy-to-use CPM for Chinese text generation（基于CPM的中文文本生成）

This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and training code.

The most advanced AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the co…

Tesseract Open Source OCR Engine (main repository)

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

[EMNLP 2023] Knowledge Rumination for Pre-trained Language Models

ModelScope: bring the notion of Model-as-a-Service to life.

[ACL 2024] A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.