Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
151.
▲
ml-engineering/training/performance
(github.com/stas00)
2 points
lordswork
10 months ago
discuss
152.
▲
Lessons learned from training 104B model
(github.com/bigscience-workshop)
2 points
EvgeniyZh
4 years ago
discuss
153.
▲
Radare2 from a to Z (extended edition) [reverse engineering]
(github.com/radareorg)
2 points
j_s
10 years ago
discuss
154.
▲
MNIST Training in C# – Deep Learning
(github.com/deepakkumar1984)
1 point
siadroid
9 years ago
discuss
155.
▲
Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformers
189 points
areddyyt
2 years ago
79 comments
156.
▲
Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
(nature.com)
153 points
onasta
a year ago
44 comments
157.
▲
Show HN: ART – a new open-source RL framework for training agents
(github.com/OpenPipe)
116 points
kcorbitt
a year ago
12 comments
158.
▲
IG65M-PyTorch: video models pre-trained on over 65M Instagram videos
10 points
danieljh
7 years ago
discuss
159.
▲
Show HN: Syna – Minimal ML and RL Framework Built from Scratch with NumPy
(github.com/sql-hkr)
8 points
sql-hkr
8 months ago
discuss
160.
▲
Ask HN: AI Voice Reverse
3 points
loregate
2 years ago
5 comments
161.
▲
Show HN: RETVec: Resilient and Efficient Text Vectorizer
3 points
ebursztein
3 years ago
discuss
162.
▲
Transformer from scratch HTTPS://github.com/Eamon2009/Transformer-language-model
2 points
Eamon_Sippy
2 months ago
discuss
163.
▲
Full forward pass of GPT-2 in one file of pure CUDA
(github.com/karpathy)
63 points
tosh
2 years ago
4 comments
164.
▲
Show HN: 6DoF Object detection and tracking in web browser – WebAR.rocks.train
(github.com/WebAR-rocks)
12 points
xavierwebgl
a year ago
discuss
165.
▲
Show HN: MXNet Implementation of Quantization Aware Training
(github.com/Ldpe2G)
2 points
Ldpe2G
7 years ago
discuss
166.
▲
How Are My Hyperparameters Affecting My Training Time?
(github.com/sigopt)
2 points
alexcmu
10 years ago
discuss
167.
▲
Hands-on workshops and training sessions at Universe
(github.com/blog)
1 point
dwaxe
10 years ago
discuss
168.
▲
Llm.c – LLM training in simple, pure C/CUDA
(github.com/karpathy)
1050 points
tosh
2 years ago
168 comments
169.
▲
History LLMs: Models trained exclusively on pre-1913 texts
(github.com/DGoettlich)
897 points
iamwil
6 months ago
421 comments
170.
▲
If you don't opt out by Apr 24 GitHub will train on your private repos
745 points
vmg12
2 months ago
316 comments
171.
▲
TimeCapsuleLLM: LLM trained only on data from 1800-1875
(github.com/haykgrigo3)
737 points
admp
5 months ago
314 comments
172.
▲
Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa
(github.com/nomic-ai)
593 points
qeternity
3 years ago
301 comments
173.
▲
DeepSeek open source DeepEP – library for MoE training and Inference
(github.com/deepseek-ai)
536 points
helloericsf
a year ago
71 comments
174.
▲
CoreNet: A library for training deep neural networks
(github.com/apple)
494 points
rocauc
2 years ago
131 comments
175.
▲
Train Your Own LLM from Scratch
(github.com/angelos-p)
478 points
kristianpaul
a month ago
50 comments
176.
▲
SmolGPT: A minimal PyTorch implementation for training a small LLM from scratch
(github.com/Om-Alve)
434 points
amrrs
a year ago
55 comments
177.
▲
Show HN: Every Breath You Take – Heart Rate Variability Training
(github.com/kbre93)
348 points
kbre93
3 years ago
118 comments
178.
▲
Databricks Releases 15K Record Training Corpus for Instruction Tuning LLMs
(github.com/databrickslabs)
347 points
xatalytic
3 years ago
89 comments
179.
▲
Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
(github.com/alainnothere)
265 points
xlayn
3 months ago
80 comments
180.
▲
Full LLM training and evaluation toolkit
(github.com/huggingface)
249 points
testerui
2 years ago
6 comments
More