HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
601.
▲
The simplest, fastest repository for training/finetuning small-sized VLMs
github.com/huggingface
discuss
a year ago
s-macke
2 points
602.
▲
Training a SOTA 7B LRM with 1.5x Throughput Improvment
github.com/inclusionAI
discuss
a year ago
jinqueeny
2 points
603.
▲
Diffusion-pipe: A pipeline parallel training script for diffusion models
github.com/tdrussell
discuss
a year ago
danboarder
2 points
604.
▲
SynCity: Training-Free Generation of 3D Worlds
github.com/paulengstler
discuss
a year ago
cal85
2 points
605.
▲
Smalldiffusion: Readable code for training and sampling from diffusion models
github.com/yuanchenyang
discuss
a year ago
sebg
2 points
606.
▲
SpeciesNet: AI models trained by Google to classify species in images
github.com/google
discuss
a year ago
croes
2 points
607.
▲
Microsoft releases TRELLIS dataset: 500k 3D assets for model generation training
github.com/microsoft
discuss
a year ago
summarity
2 points
608.
▲
Autotrain: Sota model training, open source, no code
github.com/huggingface
discuss
2 years ago
abhi1thakur
2 points
609.
▲
Apple ML – Reduce LLM training memory without speed loss
github.com/apple
discuss
2 years ago
taikon
2 points
610.
▲
Blotz 1: a trainable, MIT License Alphafold3 alternative
github.com/jwohlwend
discuss
2 years ago
Protostome
2 points
611.
▲
Show HN: Polaris – Training On-Device AI Agents with Real User Data
github.com/cyrilzakka
discuss
2 years ago
archiv
2 points
612.
▲
Pax: A Jax-based machine learning framework for training large scale models
github.com/google
discuss
2 years ago
lnyan
2 points
613.
▲
Dead Simple Web UI for Training Flux LoRA with Low VRAM (12GB/16GB/20GB) Support
github.com/cocktailpeanut
discuss
2 years ago
cocktailpeanut
2 points
614.
▲
Distributed Training over the Internet [pdf]
github.com/NousResearch
discuss
2 years ago
FergusArgyll
2 points
615.
▲
Preliminary Report on DisTrO (Distributed Training Over-the-Internet) [pdf]
github.com/NousResearch
discuss
2 years ago
jasondavies
2 points
616.
▲
Liger Kernel: One line to make LLM Training and20% faster and -60% memory
github.com/linkedin
discuss
2 years ago
byhsu
2 points
617.
▲
TraDiffusion:Trajectory-Based Training-Free Image Generation
github.com/och-mac
discuss
2 years ago
lnyan
2 points
618.
▲
Show HN: Deep learning framework from scratch, trains GPT-2 in 3 days
github.com/bclarkson-code
discuss
2 years ago
netwrt
2 points
619.
▲
Show HN: Supamodel -- monitor ML training sessions on your iPhone
supamodel.ai
discuss
2 years ago
sarangzambare
2 points
620.
▲
Show HN: I reproduced Code Llama fill-in-the-middle code completion training
github.com/BohdanPetryshyn
discuss
2 years ago
BohdanPetryshyn
2 points
621.
▲
Train an AI voice model in 10 minutes
github.com/RVC-Project
discuss
2 years ago
ambigious7777
2 points
622.
▲
Fish-Speech 1.1: Llama-based TTS trained on 150K hours of trilingual speach data
github.com/fishaudio
discuss
2 years ago
nicognaw
2 points
623.
▲
Train a Low Cost Robot Arm with <30 Demonstrations
github.com/Shaka-Labs
discuss
2 years ago
vateseif
2 points
624.
▲
StarCoder: A language model trained on source code and natural language text
github.com/bigcode-project
discuss
2 years ago
tosh
2 points
625.
▲
The Era of 1-Bit LLMs: Training Tips, Code And FAQ [pdf]
github.com/microsoft
discuss
2 years ago
histories
2 points
626.
▲
The Era of 1 Bit LLMs – Training, Tips, Code [pdf]
github.com/microsoft
discuss
2 years ago
netsec_burn
2 points
627.
▲
Unified Training of Universal Time Series Forecasting Transformers
github.com/SalesforceAIResearch
discuss
2 years ago
gorold
2 points
628.
▲
Text Generation with Ted – Trainable Exponential Decay(s)
github.com/blpj
discuss
2 years ago
anotherpaulg
2 points
629.
▲
Show HN: Train a GPT to write like Shakespeare-from scratch, in one Python file
gist.github.com
discuss
2 years ago
s-casci
2 points
630.
▲
Reference Architecture for ML Training and Batch on GKE with Kueue
github.com/GoogleCloudPlatform
discuss
2 years ago
smarterclayton
2 points
More