个人中文简历 Latex 源码 https://hijiangtao.github.io/

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

A Retrieval-Augmented Generation system built on 50k+ Formula 1 records — ask natural language questions, get fast, accurate, confidence-scored answers.

用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.

A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.

CMB, A Comprehensive Medical Benchmark in Chinese

HuatuoGPT, Towards Taming Language Models To Be a Doctor. (An Open Medical GPT)

offical repository of LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

OpenMMLab Detection Toolbox and Benchmark

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

互联网仍有记忆！那些曾经在校招过程中毁过口头offer、意向书、三方的公司！纵然人微言轻，也想尽绵薄之力！

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Fast and memory-efficient exact attention

中文翻译的 Hands-On-Large-Language-Models (hands-on-llms)，动手学习大模型

复现大模型相关算法及一些学习记录

verl: Volcano Engine Reinforcement Learning for LLMs

Minimal reproduction of DeepSeek R1-Zero

Practice to LLM.

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

本项目设计了一个基于 RAG 与大模型技术的医疗问答系统，利用 DiseaseKG 数据集与 Neo4j 构 建知识图谱，结合 BERT 的命名实体识别和 34b 大模型的意图识别，通过精确的知识检索和问答生成， 提升系统在医疗咨询中的性能，解决大模型在医疗领域应用的可靠性问题。

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

A framework for few-shot evaluation of language models.

Datawhale成员整理的面经，内容包括机器学习，CV，NLP，推荐，开发等，欢迎大家star

A framework for large scale recommendation algorithms.

key Deep Learning engineering tricks in recsys

A Survey of Reinforcement Learning for Large Reasoning Models

SMPISD-MTPNet: Scene Semantic Prior-Assisted Infrared Ship Detection Using Multi-Task Perception Networks