最有价值项目

Vim Speech Recognition Experiments

Natural Language Processing Nanodegree from Udacity Platform, in which I implement Hidden Markov Model for POS Tagger, Bidirectional LSTM for English-French Machine Translation, and End-to-End LSTM-based Speech Recognition

Turn CAPSLOCK key into Dictation Key

Python SDKs for Speechmatics APIs

htop for your LLM inference cluster

Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System

A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → parallelism → vLLM/SGLang, with GPU labs on open models.

RAG using LlamaIndex：Computer Network Q&A System powered by LlamaIndex | 基于 LlamaIndex 框架的计算机网络智能问答系统 - HyDE+混合检索 + vLLM 推理+Ragas评估

Network-faithful simulation of LLM serving and training deployments

Set of fast LINQ-like extension methods for arrays and lists. Fine-tune your code for the maximum performance.

Deterministic AI defense framework: immutable input filtering, n-model cryptographic hash consensus, and self-learning adaptive rules. Zero dependencies. Hardware-sealed. Patent Pending.

Collect and maintain high quality instruction finetune datasets in different domain and languages. 搜集並維護高品質各專業領域及語言的指令微調資料集

This repository provides an easy way to train your models on the datasets of DCASE task 1.

Investigating the role of pre-training dataset size and diversity on the performance of single-cell foundation models

Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, deduplication, and flexible export.

Implementation of build an LLM from scratch by Sebastian Raschka.

Fine-tuning open-source large and small instruct/chat language models (LLMs & SLMs) from the Hugging Face Model Hub using public datasets.

⚡ A seamless integration of HuggingFace Transformers & Diffusers with RBLN SDK for efficient inference on RBLN NPUs.

An AI-enhanced, voice enabled, searchable, sortable Task App with dark mode support. Built with Appwrite, React, Typescript and Tailwind.