Xceron's Stars
carlini/yet-another-applied-llm-benchmark
A benchmark to evaluate language models on questions I've previously asked them to solve.
google-research/tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
wi2trier/gpu-server
System configuration for a CUDA-based GPU server using Nix
xjdr-alt/entropix
Entropy Based Sampling and Parallel CoT Decoding
InSyncWithFoo/ryecharm
The all-in-one PyCharm plugin for Astral-backed Python tools
AnswerDotAI/fasthtml
The fastest way to create an HTML app
astral-sh/uv
An extremely fast Python package and project manager, written in Rust.
daylinmorgan/viv
viv isn't venv
LAION-AI/Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
BlinkDL/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
anoopkcn/obsidian-reference-map
Reference and citation map for literature review and discovery
PipedreamHQ/pipedream
Connect APIs, remarkably fast. Free for developers.
ciderapp/Cider
🎵 Source code for Cider 1
deepfates/silicon
Add some intelligence to your notes with Silicon AI for Obsidian
facebook/ktfmt
A program that reformats Kotlin source code to comply with the common community standard for Kotlin code conventions.
tfeldmann/organize
The file management automation tool.
maid/maid
Be lazy. Let Maid clean up after you, based on rules you define. Think of it as "Hazel for hackers".
jesseduffield/lazydocker
The lazier way to manage everything docker