Sign in

Repository Index

111,820 visible repositories in the index

Tags: LLM tools
Tags

A repository shows when it has any selected Tag.

Clear Tags
Filters

Filters

Clear all filters

1–24 of 26 · Most stars

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

Laravel’s #1 real-time chat package. Direct messages, groups, voice notes, and much more, with a full messenger UI — plus a headless API. Install in one command.

This is the fully-functional GNU Radio software-defined radio (SDR) implementation of a LoRa transceiver with all the necessary receiver components to operate correctly even at very low SNRs. This work has been conducted at the Telecommunication Circuits Laboratory, EPFL.

An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR-2 AI (running directly on your machine).

  • ai
  • deepseek-ocr
  • english
  • llm

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.

PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.