HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
571.
▲
Show HN: I trained a neural network to learn Arabic morphology
github.com/tb0yd
40 comments
8 years ago
tboyd47
183 points
572.
▲
Launch HN: Flower (YC W23) – Train AI models on distributed or sensitive data
69 comments
3 years ago
niclane7
180 points
573.
▲
Show HN: A Python tool for text-based AI training and generation using GPT-2
github.com/minimaxir
41 comments
6 years ago
minimaxir
174 points
574.
▲
Show HN: OCR pipeline for ML training (tables, diagrams, math, multilingual)
github.com/ses4255
38 comments
a year ago
ses425500000
170 points
575.
▲
Show HN: Breathe – Peripheral Breath Trainer
github.com/filipeisho
69 comments
6 years ago
filipeisho
167 points
576.
▲
Understanding R1-Zero-Like Training: A Critical Perspective
github.com/sail-sg
21 comments
a year ago
pama
160 points
577.
▲
Forth implemented in Rust trait system
github.com/Ashymad
84 comments
6 years ago
Ashymad
157 points
578.
▲
Train CIFAR10 to 94% in under 10 seconds on a single A100
github.com/tysam-code
50 comments
3 years ago
tysam_and
151 points
579.
▲
Show HN: Streamdal – an open-source tail -f for your data
github.com/streamdal
37 comments
3 years ago
dsies
148 points
580.
▲
Paper Tape Is All You Need – Training a Transformer on a 1976 Minicomputer
github.com/dbrll
26 comments
3 months ago
rahen
145 points
581.
▲
Extreme video compression with prediction using pre-trainded diffusion models
github.com/ElesionKyrie
88 comments
2 years ago
john_g
144 points
582.
▲
Can Europe train a frontier AI model on the compute it owns?
github.com/sammysltd
296 comments
9 days ago
smashini
143 points
583.
▲
01-AI/Yi: A series of large language models trained from scratch
github.com/01-ai
52 comments
3 years ago
simonpure
143 points
584.
▲
Open-Llama: Complete training pipeline for building large language models
github.com/s-JoL
12 comments
3 years ago
bayes-song
141 points
585.
▲
Ask HN: Has Anyone Trained a personal LLM using their personal notes?
69 comments
2 years ago
Erazal
138 points
586.
▲
Using OpenAI Gym to train an open-source 3D printed robot
github.com/nicrusso7
26 comments
6 years ago
nicrusso7
135 points
587.
▲
Diffusion training from scratch on a micro-budget
github.com/SonyResearch
23 comments
a year ago
lnyan
135 points
588.
▲
YaFSDP: a sharded data parallelism framework, faster for pre-training LLMs
github.com/yandex
16 comments
2 years ago
wiradikusuma
135 points
589.
▲
Schedule-Free Learning – A New Way to Train
github.com/facebookresearch
43 comments
2 years ago
ironbound
131 points
590.
▲
TScale – Distributed training on consumer GPUs
github.com/Foreseerr
27 comments
a year ago
zX41ZdbW
130 points
591.
▲
TensorFlow Code for Google Research's BERT: Pre-Training Method for NLP Tasks
github.com/google-research
13 comments
8 years ago
ArtWomb
129 points
592.
▲
Show HN: Set of trained deep learning models for computer vision
github.com/fchollet
15 comments
10 years ago
fchollet
127 points
593.
▲
Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL
github.com/Danau5tin
12 comments
a year ago
Danau5tin
125 points
594.
▲
Show HN: Python decorator that enables arbitrarily-deep tail/non-tail recursion
github.com/tylerhou
21 comments
5 years ago
tylerhou
119 points
595.
▲
Tail-call optimization added to 6to5 compiler
github.com/6to5
31 comments
11 years ago
insertion
117 points
596.
▲
Training open-source LLMs on ChatGPT output is a really bad idea.
gist.github.com
76 comments
3 years ago
laprise
114 points
597.
▲
NanoGPT: The simplest, fastest repository for training medium-sized GPTs
github.com/karpathy
21 comments
2 years ago
ulrischa
114 points
598.
▲
How to Train and Build a Conversational News Chatbot
github.com/tzano
8 comments
8 years ago
tzano
108 points
599.
▲
List of European train stations and associated metadata
github.com/capitainetrain
55 comments
11 years ago
thibaut_barrere
107 points
600.
▲
Show HN: Ts-SSH – SSH over Tailscale without running the daemon
github.com/derekg
37 comments
a year ago
i8code
103 points
More