🤖 Machine Learning - buckman · Scour

83. HuggingFace: Your Library for Every Pretrained Model 🤗Hugging Face

dev.to·4d·DEV

AlexRosito67/xyron-mnist-esp32: Implementation of Xyron (Neural network CLI tool in C++ with configurable layers and activation functions) 📶ESP32

github.com·22h·DEV

AI Paper Review: Language Models are Few-Shot Learners (GPT-3) 🤖Large Language Models

freecodecamp.org·2d

Synthetic Persona Pretraining: Alignment from Token Zero 🛡️AI Safety

lesswrong.com·14h

Deep Learning Weekly: Issue 455 🤖LLM Inference

deeplearningweekly.com·6d

Implications Of Predicting The Next Token 💬NLP

lesswrong.com·1d

92. BERT: The Model That Reads in Both Directions 🤖Transformer Architecture

dev.to·6h·DEV

87. Build a Chatbot: From Zero to Working AI Assistant 💬NLP

dev.to·2d·DEV

Keyless Deep Learning Steganography: Replacing Spread Spectrum Keys with CNNs 🕵️‍♂️ 🧠Deep Learning

dev.to·15h·DEV

90. Phase 8 Capstone: Build a Full AI Application 💬NLP

dev.to·1d·DEV

84. Fine-Tuning LLMs: Teaching Giants New Tricks 🧠LLM Training

dev.to·4d·DEV

I Thought Fine-Tuning LLMs Needed Expensive GPUs. I Was Wrong. 🤖LLM Inference

dev.to·21h·DEV

ML Engineer vs AI Engineer: What's Actually the Difference? 👷ML Engineering

dev.to·2d·DEV

I Fine-Tuned a Compliance Judge and Beat the Stock Model by +29.6pp F1 🛡️LLM Security

dev.to·5d·DEV

Gemma 4 Is the First Open Model I'd Actually Recommend to a Client 🦙Ollama

dev.to·1d·DEV

Building Sakhi: Hindi Voice-to-Form for India's ASHA Workers, Solo in Six Weeks 🦙Ollama

dev.to·1d·DEV

You Don't Have to Fine-Tune Your LLM to change it's Behavior. You Can Just… Steer It. ✍️Prompt Engineering

dev.to·6d·DEV

Should You Use RAG or Fine-Tune Your LLM? 💰Compute Costs

dev.to·1d·DEV

AI Engineer vs Machine Learning Engineer in 2026: Salary, Skills 👷ML Engineering

dev.to·5d·DEV

81. BERT: Understanding Language Deeply 🤖Transformers

dev.to·5d·DEV

No more posts from buckman's subscribed feeds.

Scour all 24660 feeds Learn more about Feeds

Log in to enable infinite scrolling