HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
721.
▲
Show HN: SparseLab–real sparse training(CSR+custom kernel) in PyTorch, CPU-first
news.ycombinator.com
1 comment
2 months ago
DARSHANFOFADIYA
1 points
722.
▲
Show HN: I built a visual ML trainer that exports to standalone PyTorch code
github.com/zaina-ml
1 comment
3 months ago
zaina-ml
1 points
723.
▲
Show HN: Finding stragglers in multi-GPU PyTorch (DDP) training
github.com/traceopt-ai
1 comment
5 months ago
traceopt-ai
1 points
724.
▲
Show HN: LayerClaw – Lightweight observability for PyTorch training runs
github.com/layerclaw
1 comment
5 months ago
prabhavsanga
1 points
725.
▲
CW/Morse Code Trainer Inspired by G4FON
github.com/jhnhnsn
1 comment
5 months ago
jhnhnsn
1 points
726.
▲
SkyLaunch – open-source flight training tracker for student pilots
github.com/unshah
1 comment
5 months ago
unshah
1 points
727.
▲
I trained a 90-day weather AI on a single GPU using 150 years of data
github.com/consigcody94
1 comment
5 months ago
sentinelowl
1 points
728.
▲
Show HN: TraceML, a tool to trace live memory usage in PyTorch training
github.com/traceopt-ai
1 comment
9 months ago
traceopt-ai
1 points
729.
▲
TickBlock: GPT-2 performance at 0.5% size, trained on a Mac, Physics-inspired
github.com/projectbelgrade
1 comment
9 months ago
ivan_icin
1 points
730.
▲
Show HN: Shannon Control Unit – Adaptive PI Control for LLM Training
github.com/Hmbown
1 comment
10 months ago
hunterbown
1 points
731.
▲
Whitepaper: Decentralized Protocol for Verifiable LLM Training and Fine-Tuning [pdf]
github.com/impulse-ai
1 comment
a year ago
ecballer17
1 points
732.
▲
GRPO experiment - I trained a Language Model to schedule events
github.com/anakin87
1 comment
a year ago
anakin87
1 points
733.
▲
Show HN: RBFleX-NAS: Training-Free Neural Architecture Search
github.com/tomomasayamasaki
1 comment
a year ago
Tomomasa
1 points
734.
▲
Understanding R1-Zero-Like Training: A Critical Perspective [pdf]
github.com/sail-sg
1 comment
a year ago
delifue
1 points
735.
▲
LLM training written in Rust, 30 times better than C implementation
github.com/Steboss
1 comment
a year ago
steboss
1 points
736.
▲
I Reproduced Inverse Reinforcement Alignment Training Method from DeepMind
github.com/sankyde
1 comment
a year ago
sankyde19999
1 points
737.
▲
Train a neural network with your Strava activities in order to predict race time
github.com/nst
1 comment
2 years ago
beefburger
1 points
738.
▲
DataFrameAndNotebooksAmsterdam2024 – Discovering why trains come in late in NL
github.com/Jolanrensen
1 comment
2 years ago
jesperancinha
1 points
739.
▲
DLRover: Distributed Deep Learning System for LLM Training
github.com/intelligent-machine-learning
1 comment
2 years ago
daemond
1 points
740.
▲
Collection of datasets to train your own multi-modal GPT-4/LLMs
github.com/yaodongC
1 comment
3 years ago
yaodong_lukas
1 points
741.
▲
StreetFighterAI: Train a StreetFighter bot with GPT4 to defeat the final boss
github.com/linyiLYi
1 comment
3 years ago
haoqian
1 points
742.
▲
NLP model trained on Indonesian Bahasa
github.com/IndoNLP
1 comment
3 years ago
wutania
1 points
743.
▲
Visualize how your neural networks change during training
github.com/erupturatis
1 comment
3 years ago
erupturatis
1 points
744.
▲
Show HN: SubwAI – an AI trained to play Subway Surfers using CNN
github.com/nikp06
1 comment
5 years ago
nikp06
1 points
745.
▲
Optimizer obsoletes step-size scheduling, 100% on MNIST's training set 11 epochs
github.com/YanaiEliyahu
1 comment
5 years ago
YanaiEliyahu
1 points
746.
▲
Monitor PyTorch and TensorFlow model training on mobile phones
github.com/lab-ml
1 comment
6 years ago
hnipun
1 points
747.
▲
ActionML Harness: open-source ML server and training engine
github.com/actionml
1 comment
6 years ago
morrishsieh
1 points
748.
▲
Train machines like it's 1979 Gesture controlled Atari 2600
github.com/nickbild
1 comment
6 years ago
nickbild
1 points
749.
▲
I Tried to Train a RNN on Donald Trumps Tweets
github.com/wyattferguson
1 comment
7 years ago
wyattferguson
1 points
750.
▲
Show HN: Generate text using a NN, or train your own of any size on any text
github.com/minimaxir
1 comment
8 years ago
minimaxir
1 points
More