Tag

#huggingface

233 posts46 followers

Explore Hashnode

Alternatives

Yong YuOct 9 · 7 min read

Liquid AI's d1 Decision Models Went Open: Triage Support Tickets on a CPU With the 600M One (and Where It Fools You)

Attributed compile + one small real CPU runPrimary sources (Liquid AI, 2026-10-07): Open d1: Edge decision models for text, vision, and audio (Liquid AI blog), Multimodal open d1 decision models for t

yongboyu.hashnode.dev

Matt MulvaneySep 29 · 5 min read

Oracle APEX Plugin for Zero Shot Classification

Zero-shot text classification is a task in natural language processing where a model is trained on a set of labeled examples but is then able to classify new examples from previously unseen classes.

1 mattmulvaney.hashnode.dev

Mohammed Yahya AhmedSep 22 · 5 min read

Choosing the Embedding Architecture for BrainZen

When I first started adding semantic search to BrainZen, I figured the actual vector search algorithms would be the biggest headache. I was wrong. The very first hurdle was a much more foundational qu

1 learningwithyahya.hashnode.dev

Muhammad Ariel ShakaramiroSep 19 · 6 min read

Text Recognition Without Training a Model at All? Try a Vision-Language Model

Table of Contents Context Guess First Why This Approach Is Different How It Works Test Results Plot Twist: An Image from the Internet Can Hang Your Notebook When This Approach Does (and Doesn't

shaka-ai.hashnode.dev

Parth krishan GoswamiSep 17 · 5 min read

Day 16: pdf_loader.ipynb — 64 Pages, 359 Chunks, 384 Dimensions

64 pages went in. 359 chunks came out, and every chunk is now a list of 384 numbers. On Day 15, loaders turned my PDFs into Document objects. Today they get cut into pieces and turned into vectors, th

parthkg.hashnode.dev

Praise JamesSep 14 · 6 min read

Integrating Zenrows into smolagents for production web access

This article was originally published on the Zenrows blog. Read the original here: https://www.zenrows.com/blog/zenrows-smolagents Architecture overview smolagents' VisitWebpageTool is built on Pytho

zenrows.hashnode.dev

Asada ShinsakuSep 12 · 24 min read

The World Was Already Moving: NVIDIA's Hugging Face Acquisition & GPT-6 (A Japanese Engineer's View)

NVIDIA agreeing to buy Hugging Face for something like thirteen billion dollars, and OpenAI shipping GPT-6 Astra, landed on the same day — September 3rd. For about twenty-four hours my feed couldn't d

guidingstar.hashnode.dev

Muhammad Ariel ShakaramiroSep 12 · 7 min read

GPT-2 From Scratch vs Fine-Tuning: A Text Generation Experiment and Its Honest Findings

There are two main ways to build a text generation model: train one from nothing, or take a model that already knows a lot and teach it something new. This post runs both, on the same small compute bu

shaka-ai.hashnode.dev

Sten PetrovAug 30 · 8 min read

OpenAI is training AI the wrong way

PHASEONE bots that escaped their sandbox are just a symptom. OpenAI (an everyone else) is about to make things a lot worse. It is possible to fix this, not just prevent the next one. The Hugging F

stenpetrov.hashnode.dev

ilya sergeevAug 17 · 9 min read

Qwen3.8: is FP8 worth it under transformers?

Cost of the Answer — issue #1. Qwen3.8-27B ships in two precisions on the HuggingFace hub. The FP8 checkpoint is roughly half the byte count of the BF16 one, and I wanted to know what that halving buy

krauncher.hashnode.dev

Search Hashnode

Explore Hashnode

Trending tags this week

Liquid AI's d1 Decision Models Went Open: Triage Support Tickets on a CPU With the 600M One (and Where It Fools You)

Oracle APEX Plugin for Zero Shot Classification

Choosing the Embedding Architecture for BrainZen

Text Recognition Without Training a Model at All? Try a Vision-Language Model

Day 16: pdf_loader.ipynb — 64 Pages, 359 Chunks, 384 Dimensions

Integrating Zenrows into smolagents for production web access

The World Was Already Moving: NVIDIA's Hugging Face Acquisition & GPT-6 (A Japanese Engineer's View)

GPT-2 From Scratch vs Fine-Tuning: A Text Generation Experiment and Its Honest Findings

OpenAI is training AI the wrong way

Qwen3.8: is FP8 worth it under transformers?