Lists (4)
Stars
A framework for few-shot evaluation of language models.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Claude在发布3.7的时候，不是顺便发了一个叫Claude Code的命令行工具么，这个工具是用nodejs实现的npm包，但源码已经过了压缩和基础混淆。不过有人发现它在 0.2.8 版本之前，居然使用的开发环境配置来打生产包，导致打来出的mjs文件有22M之大，文件巨大是因为它使用了 inline-source-map，这个玩意可以直接被反解成源码，混淆了个寂寞。随后 Claude 光…
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
🚀 Easier & Faster YOLO Deployment Toolkit for NVIDIA 🛠️
This repository give a guidline to learn CUDA and TensorRT from the beginning.
This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.
TensorRT 2022 亚军方案，tensorrt加速mobilevit模型
YOLOv12 Inference Using CPP, Tensorrt, And CUDA
tensorrt for yolo series (YOLOv11,YOLOv10,YOLOv9,YOLOv8,YOLOv7,YOLOv6,YOLOX,YOLOv5), nms plugin support
VEYE and CS series camera module bsp to NVIDIA Jetson platform
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
墨鱼去广告计划 | QuantumultX 去广告 | 去开屏广告 | 应用净化 | 会员解锁 | 墨鱼配置 | 应用增强 | 网页优化 | 网盘资源 | 模块去广告 | Shadowrocket配置 | 墨鱼规则 | Clash配置 | 小火箭去广告 | 资源库 | AdBlock | 网页广告 | 不完全指北