DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
A beginner's guide to the Qwen-Image-2.1-Turbo-Quantized model by Abenzerps on Huggingface
aimodels-fyi profile

A beginner's guide to the Qwen-Image-2.1-Turbo-Quantized model by Abenzerps on Huggingface

#coding #ai #machinelearning #programming
Comments
4 min read
Safety Rules Don’t Survive the Context Window: Quantifying and Fixing Agent Compliance Decay
priyeshdave6 profile

Safety Rules Don’t Survive the Context Window: Quantifying and Fixing Agent Compliance Decay

#ai #agenticai #machinelearning #llm
Comments
6 min read
Independent study tests Direct Nash Optimization for aligning language models
paragonaimag profile

Independent study tests Direct Nash Optimization for aligning language models

#ai #machinelearning #science #research
Comments
1 min read
I rebuilt a 1.47 MB, 761,000-parameter intent router and raced it against if statements. The if statements won
alexlee7359 profile

I rebuilt a 1.47 MB, 761,000-parameter intent router and raced it against if statements. The if statements won

#ai #llm #machinelearning #performance
Comments
12 min read
GPT-6 Astra แก้ไข Qwen3.5-0.8B ได้อย่างไร ด้วยการแก้ไขน้ำหนักโมเดลเพียง 0.016%
thanawat_wonchai profile

GPT-6 Astra แก้ไข Qwen3.5-0.8B ได้อย่างไร ด้วยการแก้ไขน้ำหนักโมเดลเพียง 0.016%

#ai #llm #machinelearning
Comments
5 min read
GPT-6 AstraがQwen3.5-0.8Bを重みの0.016%編集で修正した方法
aakira profile
Akira

GPT-6 AstraがQwen3.5-0.8Bを重みの0.016%編集で修正した方法

#ai #deeplearning #llm #machinelearning
Comments
4 min read
Bagaimana GPT-6 Astra Memperbaiki Qwen3.5-0.8B dengan Mengedit 0,016% Bobotnya
walse profile
Walse

Bagaimana GPT-6 Astra Memperbaiki Qwen3.5-0.8B dengan Mengedit 0,016% Bobotnya

#ai #deeplearning #llm #machinelearning
Comments
9 min read
How I Made a 27‑Billion‑Parameter Model Run on My MacBook Pro in Real Time – And Debugged It Live!
amrithesh_dev profile
amrit

How I Made a 27‑Billion‑Parameter Model Run on My MacBook Pro in Real Time – And Debugged It Live!

#ai #machinelearning #edgecomputing
Comments
7 min read
We tested the viral AI chart model on dates it can't have seen. No edge.
alexbsolodev profile
Alex B

We tested the viral AI chart model on dates it can't have seen. No edge.

#ai #machinelearning #finance #python
Comments
5 min read
Introducing SynthID Bio
ashish_624379625242c5d263 profile
Ashish

Introducing SynthID Bio

#ai #machinelearning #science
Comments
1 min read
LoRA vs QLoRA: which should you use to fine-tune an LLM?
viswaretas_kotra profile

LoRA vs QLoRA: which should you use to fine-tune an LLM?

#machinelearning #llm #gpu #ai
Comments
8 min read
Model Soups: Why Averaging Fine-Tuned Weights Beats Picking the Best One
umeshtharukaofficial profile

Model Soups: Why Averaging Fine-Tuned Weights Beats Picking the Best One

#machinelearning #datascience #ai #deeplearning
Comments
7 min read
Ricursive's Ripple-65B Preview Is a Dense 65B Open Model From a Chip-Design Startup — Explained Honestly
paullovelace profile

Ricursive's Ripple-65B Preview Is a Dense 65B Open Model From a Chip-Design Startup — Explained Honestly

#ai #opensource #machinelearning #programming
Comments 2
6 min read
Introducing SynthID Bio
ashish_624379625242c5d263 profile
Ashish

Introducing SynthID Bio

#ai #machinelearning #science
Comments
1 min read
本地 Qwen 3.8 27B 能仅凭权重识别游戏吗？
arthur1988 profile
arthur

本地 Qwen 3.8 27B 能仅凭权重识别游戏吗？

#llm #qwen #machinelearning #reinforcementlearning
Comments
1 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.