Search: github.com/ftrain | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

181.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training

github.com/alainnothere

3 months ago

265 points

182.

Full LLM training and evaluation toolkit

github.com/huggingface

2 years ago

249 points

183.

Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

github.com/NVlabs

5 years ago

243 points

184.

DeepSpeed Chat: Easy, fast and affordable RLHF training of ChatGPT-like models

github.com/microsoft

3 years ago

240 points

185.

LLMs can see and hear without any training

github.com/facebookresearch

a year ago

210 points

186.

Autoresearch: Agents researching on single-GPU nanochat training automatically

github.com/karpathy

4 months ago

208 points

187.

Keras.js – Run trained Keras models in your browser

github.com/transcranial

10 years ago

192 points

188.

Show HN: I trained a neural network to learn Arabic morphology

github.com/tb0yd

8 years ago

183 points

189.

Launch HN: Flower (YC W23) – Train AI models on distributed or sensitive data

3 years ago

180 points

190.

Show HN: A Python tool for text-based AI training and generation using GPT-2

github.com/minimaxir

6 years ago

174 points

191.

Show HN: OCR pipeline for ML training (tables, diagrams, math, multilingual)

github.com/ses4255

a year ago

170 points

192.

Show HN: Breathe – Peripheral Breath Trainer

github.com/filipeisho

6 years ago

167 points

193.

Understanding R1-Zero-Like Training: A Critical Perspective

github.com/sail-sg

a year ago

160 points

194.

Train CIFAR10 to 94% in under 10 seconds on a single A100

github.com/tysam-code

3 years ago

151 points

195.

Paper Tape Is All You Need – Training a Transformer on a 1976 Minicomputer

github.com/dbrll

3 months ago

145 points

196.

Extreme video compression with prediction using pre-trainded diffusion models

github.com/ElesionKyrie

2 years ago

144 points

197.

Can Europe train a frontier AI model on the compute it owns?

github.com/sammysltd

8 days ago

143 points

198.

01-AI/Yi: A series of large language models trained from scratch

github.com/01-ai

3 years ago

143 points

199.

Open-Llama: Complete training pipeline for building large language models

github.com/s-JoL

3 years ago

141 points

200.

Ask HN: Has Anyone Trained a personal LLM using their personal notes?

2 years ago

138 points

201.

Using OpenAI Gym to train an open-source 3D printed robot

github.com/nicrusso7

6 years ago

135 points

202.

Diffusion training from scratch on a micro-budget

github.com/SonyResearch

a year ago

135 points

203.

YaFSDP: a sharded data parallelism framework, faster for pre-training LLMs

github.com/yandex

2 years ago

135 points

204.

Schedule-Free Learning – A New Way to Train

github.com/facebookresearch

2 years ago

131 points

205.

TScale – Distributed training on consumer GPUs

github.com/Foreseerr

a year ago

130 points

206.

TensorFlow Code for Google Research's BERT: Pre-Training Method for NLP Tasks

github.com/google-research

8 years ago

129 points

207.

Show HN: Set of trained deep learning models for computer vision

github.com/fchollet

10 years ago

127 points

208.

Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL

github.com/Danau5tin

a year ago

125 points

209.

Training open-source LLMs on ChatGPT output is a really bad idea.

gist.github.com

3 years ago

114 points

210.

NanoGPT: The simplest, fastest repository for training medium-sized GPTs

github.com/karpathy

2 years ago

114 points