Khankindle's Stars
keras-team/keras
Deep Learning for humans
fastai/fastai
The fastai deep learning library
Doriandarko/claude-engineer
Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capabilities of a large language model with practical file system operations and web search functionality.
Khankindle/LangNav
Codebase for LangNav paper
pbw-Berwin/LangNav
Codebase for LangNav paper
SkalskiP/top-cvpr-2024-papers
This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]
Khankindle/LLM101n
LLM101n: Let's build a Storyteller
karpathy/LLM101n
LLM101n: Let's build a Storyteller
Khankindle/local-intelligence
Something similar to Apple Intelligence?
beratcmn/local-intelligence
Something similar to Apple Intelligence?
Khankindle/GPTand11Labs
Doriandarko/GPTand11Labs
Doriandarko/mlx-local-server
A tiny server to run local inference on MLX model in the style of OpenAI
Khankindle/DIY-Astra
Doriandarko/DIY-Astra
Doriandarko/maestro
A framework for Claude Opus to intelligently orchestrate subagents.
Atten4Vis/LW-DETR
This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".
facebookresearch/chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
apple/ml-4m
4M: Massively Multimodal Masked Modeling
predibase/lorax
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
DigitalPhonetics/IMS-Toucan
Multilingual and Controllable Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart.
intel/neural-speed
An innovative library for efficient LLM inference via low-bit quantization
Khankindle/auto-round
SOTA Weight-only Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"
intel/auto-round
SOTA Weight-only Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"
intel/intel-extension-for-transformers
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Khankindle/axlearn
An Extensible Deep Learning Library
apple/axlearn
An Extensible Deep Learning Library
ridgerchu/matmulfreellm
Implementation for MatMul-free LM.
openvla/openvla
OpenVLA: An open-source vision-language-action model for robotic manipulation.