Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
871.
▲
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
(github.com/antoinezambelli)
687 points
zambelli
25 days ago
252 comments
872.
▲
Running large language models like ChatGPT on a single GPU
(github.com/Ying1123)
682 points
_nhynes
3 years ago
264 comments
873.
▲
Show HN: Dia, an open-weights TTS model for generating realistic dialogue
(github.com/nari-labs)
652 points
toebee
a year ago
190 comments
874.
▲
GPT-J-6B – A 6 billion parameter, autoregressive text generation model
(github.com/kingoflolz)
636 points
canada_dry
5 years ago
146 comments
875.
▲
Ferret: A Multimodal Large Language Model
(github.com/apple)
621 points
weirdcat
2 years ago
308 comments
876.
▲
FreeCAD: A free and open source multiplatform 3D parametric modeler
(github.com/FreeCAD)
619 points
marcobambini
6 years ago
268 comments
877.
▲
Petals: Run 100B+ language models at home bit-torrent style
(github.com/bigscience-workshop)
594 points
antman
3 years ago
155 comments
878.
▲
Qwen3-Omni: Native Omni AI model for text, image and video
(github.com/QwenLM)
571 points
meetpateltech
9 months ago
142 comments
879.
▲
Show HN: Three new Kitten TTS models – smallest less than 25MB
(github.com/KittenML)
561 points
rohan_joshi
3 months ago
181 comments
880.
▲
GPT Neo: open-source GPT model, with pretrained 1.3B & 2.7B weight models
(github.com/EleutherAI)
561 points
pizza
5 years ago
127 comments
881.
▲
Convert Apple NeuralHash model for CSAM Detection to ONNX
(github.com/AsuharietYgvar)
505 points
homarp
5 years ago
178 comments
882.
▲
Xiaomi MiMo Reasoning Model
(github.com/XiaomiMiMo)
482 points
thm
a year ago
193 comments
883.
▲
Top model scores may be skewed by Git history leaks in SWE-bench
(github.com/SWE-bench)
466 points
mustaphah
9 months ago
153 comments
884.
▲
Show HN: BadSeek – How to backdoor large language models
(sshh12--llm-backdoor.modal.run)
461 points
sshh12
a year ago
89 comments
885.
▲
High-res image reconstruction with latent diffusion models from human brain
(github.com/yu-takagi)
459 points
trojan13
3 years ago
155 comments
886.
▲
OpenWorm – A computational model of C. elegans worm
(github.com/openworm)
442 points
dvrp
3 years ago
152 comments
887.
▲
Gemma.cpp: lightweight, standalone C++ inference engine for Gemma models
(github.com/google)
422 points
mfiguiere
2 years ago
130 comments
888.
▲
Efficient streaming language models with attention sinks
(github.com/mit-han-lab)
421 points
guywithabowtie
3 years ago
65 comments
889.
▲
High-Speed Large Language Model Serving on PCs with Consumer-Grade GPUs
(github.com/SJTU-IPADS)
417 points
dataminer
2 years ago
83 comments
890.
▲
Bark – Text-prompted generative audio model
(github.com/suno-ai)
416 points
obi1kenobi
3 years ago
89 comments
891.
▲
Show HN: Reor – An AI note-taking app that runs models locally
(github.com/reorproject)
411 points
samlhuillier
2 years ago
102 comments
892.
▲
Apple releases open-source model that instantly turns 2D photos into 3D views
(github.com/apple)
400 points
SG-
6 months ago
202 comments
893.
▲
Show HN: Port of OpenAI's Whisper model in C/C++
(github.com/ggerganov)
399 points
ggerganov
4 years ago
87 comments
894.
▲
Z-Image: Powerful and highly efficient image generation model with 6B parameters
(github.com/Tongyi-MAI)
398 points
doener
6 months ago
157 comments
895.
▲
Flash-MoE: Running a 397B Parameter Model on a Laptop
(github.com/danveloper)
398 points
mft_
3 months ago
119 comments
896.
▲
Show HN: I modeled the Voynich Manuscript with SBERT to test for structure
(github.com/brianmg)
381 points
brig90
a year ago
132 comments
897.
▲
LaVague: Open-source Large Action Model to automate Selenium browsing
(github.com/lavague-ai)
378 points
DanyWin
2 years ago
95 comments
898.
▲
Emacs-copilot: Large language model code completion for Emacs
(github.com/jart)
377 points
yla92
2 years ago
156 comments
899.
▲
Harmony: OpenAI's response format for its open-weight model series
(github.com/openai)
374 points
meetpateltech
10 months ago
50 comments
900.
▲
FastVLM: Efficient vision encoding for vision language models
(github.com/apple)
367 points
nhod
a year ago
74 comments
More