Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
- adan
- bert-model
- convnext
- deep-learning
132,241 visible repositories in the index
49–72 of 80 · Most stars
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.
An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案,包含从训练到推理的完整代码和脚本,以及实践中积累一些经验和结论。)
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
parrot.nvim 🦜 - the plugin that brings stochastic parrots to Neovim.
[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Simple implementation of OpenAI CLIP model in PyTorch.
聚合ChatGPT官方版、ChatGPT免费版、文心一言、Poe、chatchat等多平台,支持自定义导入平台
Automatically evaluate your LLMs in Google Colab
SkyChat是一款基于中文GPT-3 api的聊天机器人项目。它可以像chatGPT一样,实现人机聊天、问答、中英文互译、对对联、写古诗等任务。| SkyChat is a Chatbot project based on Chinese GPT3 API. Like chatGPT, it can do human-machine chat, question and answer, and can also complete tasks such as Chinese-English or English-Chinese translation, content continuation, couplets, and Chinese ancient poems writing.
The project integrates the RAG and FAQ dual mechanisms, introduces intent recognition, dynamic adaptive retrieval, and the RAGAS automated evaluation system, achieving a transformation from empirical optimization to data-driven optimization.
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
🤖💬 AI SDK, extra small.
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱
The repository host gives no description.
AI Video Search Engine (RAG)
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
TranslatedAI Paper System · AI paper generation, AI paper writing, one-click paper generation, AIGC rate reduction, plagiarism similarity reduction, thesis defense PPT · OEM white-label franchise recruitment
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)