HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
601.
▲
Show HN: 2500 vision benchmarks / evals for Vision Language Models
github.com/Overshoot-ai
discuss
3 months ago
zakariaelhjouji
1 points
602.
▲
Show HN: Local Full-Rank Fine-Tuning Library for LLMs with Evolutionary Methods
github.com/floatingtrees
discuss
8 months ago
floatingtrees
1 points
603.
▲
Show HN: Vlm in 3D PC, 16 shot scanobjectnn top1 acc: 99.91
github.com/genji970
discuss
a year ago
genji970
1 points
604.
▲
Show HN: Panda.chat – A ChatGPT alternative designed to protect your privacy
panda.chat
discuss
a year ago
wwwee98
1 points
605.
▲
DeepSeek-VL2: MoE Vision-Language Models for Advanced Multimodal Understanding
github.com/deepseek-ai
7 comments
a year ago
selvan
36 points
606.
▲
Voice cloning at 37.6x real time
github.com/Jransom33
discuss
3 months ago
Jransom110
4 points
607.
▲
Show HN: VLMs Can Respond Twice as Fast Without Losing Quality
github.com/sergey-automation
2 comments
4 days ago
trykhlieb
2 points
608.
▲
Show HN: TS SDK for new PaddleOCR-VL-1.5
github.com/ocrbase-hq
discuss
5 months ago
adammajcher
2 points
609.
▲
DeepSeek VL2
github.com/deepseek-ai
discuss
2 years ago
arunbahl
1 points
610.
▲
DeepSeek-VL2: Moe Vision-Language Models for Advanced Multimodal Understanding [pdf]
github.com/deepseek-ai
discuss
2 years ago
limoce
1 points
611.
▲
Extend Twitter Bootstrap with these Bootstrap Form Helpers
vlamanna.github.com
43 comments
14 years ago
vlamanna
96 points
612.
▲
Show HN: Autobahn - Save Time on Hacker News
vlad.github.com
44 comments
14 years ago
vlad
95 points
613.
▲
I wrote a batch script to keep my 2011 ThinkPad alive for 24/7 streaming
github.com/patrick48001
7 comments
6 months ago
techenthuziast
39 points
614.
▲
Bootstrap Form Helpers now has 6 plugins including one for timezones.
vlamanna.github.com
discuss
14 years ago
vlamanna
3 points
615.
▲
Qwen2.5-VL: State-of-the-art multimodal LLM
github.com/QwenLM
discuss
a year ago
t55
3 points
616.
▲
O - JavaScript Library for Object Manipulation
vladocar.github.com
discuss
15 years ago
vladocar
3 points
617.
▲
Qwen2.5-VL
github.com/QwenLM
1 comment
a year ago
saikatsg
1 points
618.
▲
Qwen2.5-VL/Cookbooks
github.com/QwenLM
discuss
a year ago
kgwgk
1 points
619.
▲
Show HN: Composable middleware for LLM inference Optimization Passes
github.com/liquidos-ai
discuss
4 months ago
human_hack3r
7 points
620.
▲
Immutable AVL Trees
github.com/alefore
discuss
6 years ago
afc
2 points
621.
▲
Super fast and accurate image classification on edge devices
github.com/Paulescu
discuss
9 months ago
PauLabartaBajo
1 points
622.
▲
Show HN: FSST – Fast Static Symbol Table Compression Library in Go
github.com/axiomhq
2 comments
9 months ago
seiflotfy
13 points
623.
▲
Show HN: I Found a Way for Crypto Casinos to Be Fair
probablyfair.org
discuss
8 months ago
ccheshirecat
3 points
624.
▲
New Recipe: Serving Llama-2 with VLLM's OpenAI-Compatible API Server
github.com/skypilot-org
discuss
3 years ago
zhwu
1 points
625.
▲
Conway's Game Of Life in V (language to be released today)
github.com/fuyutarow
discuss
7 years ago
turrini
1 points
626.
▲
Llama.cpp Now Supports Qwen2-VL (Vision Language Model)
github.com/ggerganov
50 comments
2 years ago
BUFU
155 points
627.
▲
Show HN: Benchmarking VLMs vs. Traditional OCR
getomni.ai
40 comments
a year ago
themanmaran
146 points
628.
▲
KVarN: Native vLLM backend for KV-cache quantization by Huawei
github.com/huawei-csl
16 comments
20 days ago
theanonymousone
143 points
629.
▲
Using VLC to watch an m3u8 playlist at a URL with custom Referrer and User Agent
gist.github.com
22 comments
2 years ago
chatmasta
58 points
630.
▲
SDB Scans the Ruby Stack Without the GVL
github.com/yfractal
8 comments
a year ago
ksec
30 points
More