Tag

#huggingface

233 posts46 followers

Explore Hashnode

Alternatives

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

7 min readyongboyu.hashnode.dev

Matt MulvaneySep 29

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.

5 min readmattmulvaney.hashnode.dev

1

Mohammed Yahya AhmedSep 22

Choosing the Embedding Architecture for BrainZen

How I chose browser-side embeddings for BrainZen, comparing API, backend, and inference-server architectures and their tradeoffs.

5 min readlearningwithyahya.hashnode.dev

1

Muhammad Ariel ShakaramiroSep 19

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

Extracting license plate text with the SmolVLM vision-language model, no training required, just a natural-language prompt.

6 min readshaka-ai.hashnode.dev

Parth krishan GoswamiSep 17

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

My chunks were 1,000 characters long. The embedding model only reads the first 256 tokens.

5 min readparthkg.hashnode.dev

Praise JamesSep 14

Integrating Zenrows into smolagents for production web access

6 min readzenrows.hashnode.dev

Asada ShinsakuSep 12

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

A Japanese software engineer examines NVIDIA's Hugging Face acquisition, GPT-6 Astra, AI infrastructure concentration, and what these shifts mean for developers.

24 min readguidingstar.hashnode.dev

Muhammad Ariel ShakaramiroSep 12

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

Training GPT-2 from scratch for code generation and fine-tuning an Indonesian GPT-2 — including an unexpected overfitting twist, not just the wins.

7 min readshaka-ai.hashnode.dev

Sten PetrovAug 30

OpenAI is training AI the wrong way

OpenAI HuggingFace incident and how to train AI for alignment

8 min readstenpetrov.hashnode.dev

ilya sergeevAug 17

Qwen3.8: is FP8 worth it under transformers?

FP8 vs BF16 on Qwen3.8-27B: FP8 pays a ~30 s per-session toll plus a 7–22% steady-state penalty. Under transformers, the format is memory-only

9 min readkrauncher.hashnode.dev

Search Hashnode