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 4/71 feed RSS
17:45
2026-11-16
huggingface.co
large-language-models

Nemotron Labs Sigma distill 3B nfe8 released on Hugging Face

NVIDIA published the Nemotron-Labs-Sigma-distill-3B-nfe8 model on Hugging Face, where the model card lists it under Text Generation at 4B parameters and shows it updated 4 days ago with 7 downloads. T…

10:02
2026-11-16
huggingface.co
ai-tools

Werkbank: 40 tasks for testing local LLMs with tools

A hobbyist developer released Werkbank, a set of 40 fixed, synthetic tasks for testing local large language models on multi-step tool use, with deterministic checks of final state, code or answer inst…

23:46
2026-11-15
huggingface.co
robotics

Report Cards #01 — Three public LeRobot datasets, audited

RoboAudit 0.2.x, a health-check CLI for LeRobot robot-learning datasets, published its first three public report cards, scoring `lerobot/aloha_sim_transfer_cube_scripted` at keep 48 / review 2 / exclu…

06:12
2026-11-15
huggingface.co
large-language-models

Need advice on building a chatbot

A non-technical Hugging Face forum user building a property-database RAG chatbot on Claude 4.6 via AWS Bedrock reported wrong cited numbers, hallucinations and thin answers, and was advised by forum r…

02:37
2026-11-15
huggingface.co
machine-learning

CLAP model crash after several inference iterations

A CLAP model that fails after roughly 150–300 inference slices and stays dead until a full PC restart is likely suffering from per-iteration memory growth rather than a model defect, since re-creating…

02:35
2026-11-15
huggingface.co
robotics

Building an AI robot—would love the community's input

A robot builder working on a 1 GB-class board reported that reloading a robot's full memory on each wake grew the working set by roughly 44–56% at peak, while reloading only what changed since the las…

02:34
2026-11-15
huggingface.co
ai-infrastructure

Presence: distributed AI inference across ESP32-class nodes

A critique of a distributed AI inference experiment on ESP32-class nodes argues that the swarm's 38.3-second run versus the baseline's 10.1-second run may cost more energy in waiting time than in the …

← prev page 4 / 71 next →