Skip to content

Section

LLM and language model news

Fresh language and multimodal models from Hugging Face: base, instruct and fine-tuned versions.

ullm-base: A compact 360M-parameter base LLM trained from scratch
Language models

ullm-base: A compact 360M-parameter base LLM trained from scratch

A 360-million-parameter base language model (LLM) trained from scratch using a minimalist GPT implementation called ullm by author mattiasz. It features a classical decoder-only transformer architecture and is designed solely for text continuation in English, lacking conversational formatting or…

NeyroLearn

@neyrolearn

New models from Hugging Face every morning: video, images, LoRAs and LLMs with examples and links.

Posts
1320
Tags
59
Follow on Telegram

Trending

Most liked on Hugging Face this week

  1. 1
    Add Micro Details

    Images · 8.4K

    Add Micro Details18+
  2. 2
    MiniMax-H3

    Video · 7.2K

    MiniMax-H3
  3. 3
    Flat Color - Style

    Images · 6.2K

    Flat Color - Style
  4. 4
    Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
  5. 5
    80s Fantasy Movie

    Images · 3.1K

    80s Fantasy Movie18+

Popular tags

All tags →

About Language models

This section covers large language models (LLMs) and multimodal models (VLMs) that understand both text and images. We watch Hugging Face every day and write up new releases: what the model can do, what it is based on, how big it is and how to run it.

Most of the models here come from the Qwen, Gemma, Llama and Mistral families, plus community fine-tunes trained for code, chat, specific languages or narrow tasks.

Looking for a specific model? Paste its name or Hugging Face link into search, or describe your task to the assistant on the home page.