--- title: "#huggingface articles | Hashnode" description: "Explore 233 articles tagged #huggingface on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/huggingface" --- Tag # #huggingface 233 posts · 46 followers [Yong Yu](https://hashnode.com/@yongbo) · [Oct 9](https://hashnode.com/posts/liquid-ai-s-d1-decision-models-went-open-triage-support-tickets-on-a-cpu-with-the-600m-one-and-where-it-fools-you/6ac8ef11a76a52b2d545521a) ### [Liquid AI's d1 Decision Models Went Open: Triage Support Tickets on a CPU With the 600M One (and Where It Fools You)](https://yongboyu.hashnode.dev/liquid-ai-s-d1-decision-models-went-open-triage-support-tickets-on-a-cpu-with-the-600m-one-and-where-it-fools-you?utm_source=hashnode&utm_medium=feed) 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 read · [yongboyu.hashnode.dev](https://yongboyu.hashnode.dev/liquid-ai-s-d1-decision-models-went-open-triage-support-tickets-on-a-cpu-with-the-600m-one-and-where-it-fools-you?utm_source=hashnode&utm_medium=feed) [Matt Mulvaney](https://hashnode.com/@lufcmattylad) · [Sep 29](https://hashnode.com/posts/oracle-apex-plugin-for-zero-shot-classification/6abbeb8aa6c0f686e78368dc) ### [Oracle APEX Plugin for Zero Shot Classification](https://mattmulvaney.hashnode.dev/oracle-apex-plugin-for-zero-shot-classification?utm_source=hashnode&utm_medium=feed) 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 read · [mattmulvaney.hashnode.dev](https://mattmulvaney.hashnode.dev/oracle-apex-plugin-for-zero-shot-classification?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/oracle-apex-plugin-for-zero-shot-classification/6abbeb8aa6c0f686e78368dc) [Mohammed Yahya Ahmed](https://hashnode.com/@yahyaahmed) · [Sep 22](https://hashnode.com/posts/choosing-the-embedding-architecture-for-brainzen/6ab2c83bfeb6439ce5f73dc5) ### [Choosing the Embedding Architecture for BrainZen](https://learningwithyahya.hashnode.dev/choosing-the-embedding-architecture-for-brainzen?utm_source=hashnode&utm_medium=feed) How I chose browser-side embeddings for BrainZen, comparing API, backend, and inference-server architectures and their tradeoffs. 5 min read · [learningwithyahya.hashnode.dev](https://learningwithyahya.hashnode.dev/choosing-the-embedding-architecture-for-brainzen?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/choosing-the-embedding-architecture-for-brainzen/6ab2c83bfeb6439ce5f73dc5) [Muhammad Ariel Shakaramiro](https://hashnode.com/@arielshakaramiro) · [Sep 19](https://hashnode.com/posts/license-plate-ocr-smolvlm/6aae1841524ad23676191058) ### [Text Recognition Without Training a Model at All? Try a Vision-Language Model](https://shaka-ai.hashnode.dev/license-plate-ocr-smolvlm?utm_source=hashnode&utm_medium=feed) Extracting license plate text with the SmolVLM vision-language model, no training required, just a natural-language prompt. 6 min read · [shaka-ai.hashnode.dev](https://shaka-ai.hashnode.dev/license-plate-ocr-smolvlm?utm_source=hashnode&utm_medium=feed) [Parth krishan Goswami](https://hashnode.com/@ParthKG) · [Sep 17](https://hashnode.com/posts/day-16-pdf-loader-ipynb-64-pages-359-chunks-384-dimensions/6aac1b37beea30b49c66cc09) ### [Day 16: pdf\_loader.ipynb — 64 Pages, 359 Chunks, 384 Dimensions](https://parthkg.hashnode.dev/day-16-pdf-loader-ipynb-64-pages-359-chunks-384-dimensions?utm_source=hashnode&utm_medium=feed) My chunks were 1,000 characters long. The embedding model only reads the first 256 tokens. 5 min read · [parthkg.hashnode.dev](https://parthkg.hashnode.dev/day-16-pdf-loader-ipynb-64-pages-359-chunks-384-dimensions?utm_source=hashnode&utm_medium=feed) [Praise James](https://hashnode.com/@thepraisejames) · [Sep 14](https://hashnode.com/posts/integrating-zenrows-into-smolagents-for-production-web-access/6aa7e1447af77035f27c3b01) ### [Integrating Zenrows into smolagents for production web access](https://zenrows.hashnode.dev/integrating-zenrows-into-smolagents-for-production-web-access?utm_source=hashnode&utm_medium=feed) Integrating Zenrows into smolagents for production web access 6 min read · [zenrows.hashnode.dev](https://zenrows.hashnode.dev/integrating-zenrows-into-smolagents-for-production-web-access?utm_source=hashnode&utm_medium=feed) [Asada Shinsaku](https://hashnode.com/@ishimoto) · [Sep 12](https://hashnode.com/posts/the-world-was-already-moving-nvidia-s-hugging-face-acquisition-gpt-6-a-japanese-engineer-s-view/6aa53fbac5f60040945e75b5) ### [The World Was Already Moving: NVIDIA's Hugging Face Acquisition & GPT-6 (A Japanese Engineer's View)](https://guidingstar.hashnode.dev/the-world-was-already-moving-nvidia-s-hugging-face-acquisition-gpt-6-a-japanese-engineer-s-view?utm_source=hashnode&utm_medium=feed) 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 read · [guidingstar.hashnode.dev](https://guidingstar.hashnode.dev/the-world-was-already-moving-nvidia-s-hugging-face-acquisition-gpt-6-a-japanese-engineer-s-view?utm_source=hashnode&utm_medium=feed) [Muhammad Ariel Shakaramiro](https://hashnode.com/@arielshakaramiro) · [Sep 12](https://hashnode.com/posts/gpt2-from-scratch-vs-fine-tuning-text-generation/6aa55ffafb74241e7350759b) ### [GPT-2 From Scratch vs Fine-Tuning: A Text Generation Experiment and Its Honest Findings](https://shaka-ai.hashnode.dev/gpt2-from-scratch-vs-fine-tuning-text-generation?utm_source=hashnode&utm_medium=feed) 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 read · [shaka-ai.hashnode.dev](https://shaka-ai.hashnode.dev/gpt2-from-scratch-vs-fine-tuning-text-generation?utm_source=hashnode&utm_medium=feed) [Sten Petrov](https://hashnode.com/@stenpetrov) · [Aug 30](https://hashnode.com/posts/openai-is-training-ai-the-wrong-way/6a949d37e35507474206e873) ### [OpenAI is training AI the wrong way](https://stenpetrov.hashnode.dev/openai-is-training-ai-the-wrong-way?utm_source=hashnode&utm_medium=feed) OpenAI HuggingFace incident and how to train AI for alignment 8 min read · [stenpetrov.hashnode.dev](https://stenpetrov.hashnode.dev/openai-is-training-ai-the-wrong-way?utm_source=hashnode&utm_medium=feed) [ilya sergeev](https://hashnode.com/@krauncher) · [Aug 17](https://hashnode.com/posts/qwen3-8-is-fp8-worth-it-under-transformers/6a82f71b2f6da29b5faea685) ### [Qwen3.8: is FP8 worth it under transformers?](https://krauncher.hashnode.dev/qwen3-8-is-fp8-worth-it-under-transformers?utm_source=hashnode&utm_medium=feed) 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 read · [krauncher.hashnode.dev](https://krauncher.hashnode.dev/qwen3-8-is-fp8-worth-it-under-transformers?utm_source=hashnode&utm_medium=feed)