LLMRepos·Domain-Specific Models LLM projects

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

A benchmark for LLMs on complicated tasks in the terminal

TigerBot: A multi-language multi-task LLM

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

中文法律LLaMA (LLaMA for Chinese legel domain)

Pretrained model hub for Keras 3.

An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型，GPU部署，数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM

A series of top performing Text to SQL LLMs

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

🌟 ChatGenTitle：使用百万arXiv论文信息在LLaMA模型上进行微调的论文题目生成模型

[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.

QiZhenGPT: An Open Source Chinese Medical Large Language Model｜一个开源的中文医疗大语言模型

基于Stable Diffusion优化的AI绘画模型。支持输入中英文文本，可生成多种现代艺术风格的高质量图像。| An optimized text-to-image model based on Stable Diffusion. Both Chinese and English text inputs are available to generate images. The model can generate high-quality images in several modern art styles.

T2F: text to face generation using Deep Learning

Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", CVPR 2024; 3D Avatar Generation and Animation

Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.

[VLDB' 25] Synthesizing High-quality Text-to-SQL Data at Scale. SynSQL-2.5M is the first million-scale cross-domain text-to-SQL dataset.

AutoAudit—— the LLM for Cyber Security 网络安全大语言模型

NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRaven-13B and baselines.

"DeepInnovator: AI Research Assistant - Idea Spark & Scientific Discovery"

Dự án bao gồm: 1. Xây dựng bộ dữ Instructions Vietnamese (chất lượng, nhiều, và đa dạng). 2.LLM Training, Finetuning, Evaluating & Testing trên Open-source mô hình ngôn ngữ: Bloomz,T5, UL2, LLaMA (1&2), OpenLLaMA, GPT-J pythia etc. 3. Ứng dụng và Giao diện Người dùng (UI)

A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题

Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

A fine-tuned model from Qwen2.5-1.5B-Instruct, capable of handling sensitive topics. / 从 Qwen2.5-1.5B-Instruct 微调，主要擅长处理色情话题

Numbers Station Text to SQL model code.

"QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks"

Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.

DIffbot LLM Inference Server

a comprehensive and critical synthesis of the emerging role of GenAI across the full autonomous driving stack

基于已有基座模型微调的算命大模型

A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.

Awesome music generation model——MG²

Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"

Comprehensive Compilation of Real-World LLM & AI Agent Use Cases in Financial Services

Official Code for "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023)"

Cyber-Zero: Training Cybersecurity Agents Without Runtime