Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
Repository Index
95,842 visible repositories in the index
169–192 of 226 · Most stars
把英文论文读成舒服的中文:本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.
- academic
- arxiv
- chinese
- claude-code
An elegent pytorch implement of transformers
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
Observe how memory shapes an answer. Pensieve is an interactive system for visualizing, interpreting, and managing how Large Language Models (LLMs) “remember” a user. It bridges the gap between model-level mechanisms and user-level understanding, making AI memory observable, explainable, and partially controllable.
LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案
- ai
- interview-practice
- interview-preparation
- interview-questions
Review AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent.
Jlama is a modern LLM inference engine for Java
轻小说机翻网站,支持网络小说/文库小说/本地小说
- kotlin
- light-novel
- translator
- chatgpt
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascent NPU, and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
- gptq
- optimum
- peft
- quantization
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).
- topic-modeling
- bert
- transformer
- embeddings
Local-first privacy guard: anonymize your documents before sharing with LLMs.
- anonymization
- gdpr
- italian
- legal-tech
Chat app for Android that supports answers from multiple LLMs at once. Bring your own API key AI client. Supports OpenAI, Anthropic, Google, and Ollama. Designed with Material3 & Compose.
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
- ai-infra
- attention
- inference-acceleration
- llm
Bringing together outstanding artificial intelligence (AI) open source projects from around the world.
LLM KV cache compression made easy
Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️
- huggingface-transformers
- language-vision
- multimodal
- pytorch
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
- ai4science
- data-generation
- llm-training
- sft-data
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment
- asr
- ctranslate2
- huggingface
- whisper
Neural Network Compression Framework for enhanced OpenVINO™ inference
- quantization
- pruning
- sparsity
- quantization-aware-training
Simple go utility to download HuggingFace Models and Datasets
- golang
- huggingface
- llm
- transformers
An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"
LeanType is an Open-source keyboard, fork of HeliBoard with additional features and customisation
- android
- gemini-api
- keyboard
- opensource
Translate a whole season of subtitles in one pass — .srt/.ass/.vtt/.lrc, 120+ languages, 27 LLM providers, timing untouched | 整季字幕一次译完,时轴不动,支持 120+ 语言
- srt
- subtitles
- ass
- lrc