-
tokenizer.cpp Public
A lightweight, production-ready C++ library for LLM tokenization, fully compatible with HuggingFace tokenizer.json.
-
jinja.cpp Public
A lightweight, single-header C++11 Jinja2 template engine for LLM chat templates.
-
MNN Public
Forked from alibaba/MNNMNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
-
-
-
-
minimind Public
Forked from jingyaogong/minimind🚀🚀 「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!
-
SpecForge Public
Forked from sgl-project/SpecForgeTrain speculative decoding models effortlessly and port them smoothly to SGLang serving.
-
llm-export Public
llm-export can export llm model to onnx.
-
nanochat Public
Forked from karpathy/nanochatThe best ChatGPT that $100 can buy.
Python UpdatedOct 16, 2025 -
nndeploy Public
Forked from nndeploy/nndeploynndeploy是一款最新上线的支持多平台、简单易用、高性能的机器学习部署框架，一套实现可在多端(云、边、端)完成模型的高性能部署。
-
-
md2zhihu Public
Forked from drmingdrmer/md2zhihuconvert markdown to zhihu compatible format.
-
huggingface.js Public
Forked from huggingface/huggingface.jsUse Hugging Face with JavaScript
TypeScript MIT License UpdatedJul 16, 2025 -
EAGLE Public
Forked from SafeAILab/EAGLEOfficial Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.
Python Apache License 2.0 UpdatedJun 13, 2025 -
EfficientQAT Public
Forked from OpenGVLab/EfficientQAT[ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
Python UpdatedMay 22, 2025 -
-
-
opencompass Public
Forked from open-compass/opencompassOpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Python Apache License 2.0 UpdatedMar 10, 2025 -
mnn-llm Public
llm deploy project based mnn. This project has merged into MNN.
-
-
-
ultralytics Public
Forked from ultralytics/ultralyticsUltralytics YOLO11 🚀
Python GNU Affero General Public License v3.0 UpdatedOct 30, 2024 -
-
-
Qwen2.5 Public
Forked from QwenLM/Qwen3Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
Shell UpdatedSep 19, 2024 -
-
-
mnn-segment-anything Public
segment-anything based mnn
-
{{ message }}