cd/sources/hugging-face-blog· home› sources› Hugging Face Blog
cat /sources/hugging-face-blog.feed | wc -l → 1408

Hugging Face Blog

articles 1408 domain huggingface.co → page 16/71 feed RSS
23:13
2026-10-20
huggingface.co
large-language-models

How to evaluate deceptive dialogue in LLM-based NPCs?

A practitioner guide recommends fine-tuning small language models such as LFM2.5 230M/350M or Qwen3.5 800M with QLoRA at rank 16-32 and alpha 32-64, then applying DPO with a larger model's answers as …

16:20
2026-10-20
huggingface.co
machine-learning

My first ai model

A high-school student's informal guide to getting started in machine learning recommends fine-tuning a 350M LFM model with r32 a64 LoRA rather than QLoRA, then moving to models such as qwen3.5-800M an…

10:00
2026-10-20
huggingface.co
ai-agents

N8n AI agents and workflow automation

A community guide recommends running n8n Community edition with LM Studio for free, local AI workflow automation, pointing users to the LM Studio endpoint at http://localhost:1234/v1 with any dummy AP…

00:00
2026-10-20
huggingface.co
machine-learning

MPS in PyTorch 2.15

Hugging Face's PyTorch team reported that PyTorch 2.15 brings FP8 support and 5–6.5× faster mixture-of-experts decoding to the MPS backend for Apple silicon Macs, with Qwen3.6-35B-A3B rising from 9.4 …

00:00
2026-10-20
huggingface.co
artificial-intelligence

Hugging Face ❤️ TorchTPU: TPUs, Natively

Hugging Face announced that Google's TorchTPU native PyTorch backend brings TPU support to its ecosystem, letting Transformers v5, Diffusers and Kernels run natively on TPU by sending models to the "t…

← prev page 16 / 71 next →