Pinned Repositories
drone-deploy-seg
pytorch-lightning semantic segmentation using DroneDeploy Dataset
img-cryptor
Image AES256 crypt-decrypt
kucoin-tracker
My personal crypto price tracker, in Python
licence-plate-tf
Licence plate recognition problem.
llm-weight-analyzer
Snippet for llm weight analysis
mixedbread-rag
Mixedbread large embed model, connected to chroma, simplest RAG without an LLM
self-instruct
stt-pl-common-voice
Speech to Text - Polish Language
text-detector
Tool which allow you to detect and translate text.
unet-midv500
s3nh's Repositories
s3nh/llm-weight-analyzer
Snippet for llm weight analysis
s3nh/kucoin-tracker
My personal crypto price tracker, in Python
s3nh/rl_stuff
s3nh/mixedbread-rag
Mixedbread large embed model, connected to chroma, simplest RAG without an LLM
s3nh/APOLLO
APOLLO: SGD-like Memory, AdamW-level Performance
s3nh/auto-classifier
s3nh/DistillKit
An Open Source Toolkit For LLM Distillation
s3nh/distro-simil-features
Distribution similarity between observation and population value, mealy used to measure of discrepancy between two classes.
s3nh/FasterLivePortrait
Bring portraits to life in Real Time！onnx/tensorrt support！实时肖像驱动！
s3nh/gemini-helpers
s3nh/kizuna
Fast TTS Library for Kokoro
s3nh/LLaDA
Official PyTorch implementation for "Large Language Diffusion Models"
s3nh/llm-mouth-talking
Local llm mout so you can talk with it
s3nh/ml-tarflow
s3nh/nanospeech
A simple, hackable text-to-speech system in PyTorch and MLX
s3nh/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
s3nh/picotron
Minimalistic 4D-parallelism distributed training framework for education purpose
s3nh/qlora-pipe
A pipeline parallel training script for LLMs.
s3nh/rag-dyi
spare time boring project
s3nh/s3nh-notes
s3nh/shitilike
shitilike
s3nh/smalldiffusion
Simple and readable code for training and sampling from diffusion models
s3nh/smol-course
A course on aligning smol models.
s3nh/smol-tuna
s3nh/stable-diffusion.cpp
Stable Diffusion and Flux in pure C/C++
s3nh/StableAnimator
We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.
s3nh/transformer-tricks
A collection of tricks to speed up transformer inference
s3nh/TransformerLens
A library for mechanistic interpretability of GPT-style language models
s3nh/transformers-gym
s3nh/ttt-lm-pytorch
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States