---
format: "aidr-story-markdown/v1"
id: "4bdb6d39f683fd8715294b62ab9da2482b8fe5e8330d2658d1fa50e5795ff8d7"
canonical_url: "https://aidr.today/4bdb6d39?lang=en"
title: "Hugging Face Transformers v5.24.0"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-21T12:28:26.000Z"
category: "Open Source"
topics: ["llm","open-source"]
source_urls: []
summary: "Hugging Face Transformers v5.24.0 adds Inkling 2 Mini, a multimodal model from Thinking Machines Lab that accepts text and image inputs to generate text outputs. The model features 24 decoder layers with a looping mechanism where layers 6 to 17 run three times. It includes a research checkpoint, TML-d24-varloop-research, which supports a variable number of loop passes."
---

# Hugging Face Transformers v5\.24\.0

> [Open the canonical story](<https://aidr.today/4bdb6d39?lang=en>)

**Published:** 2026-11-21T12:28:26.000Z
**Category:** Open Source
**Topics:** llm, open\-source

## Summary

Hugging Face Transformers v5\.24\.0 adds Inkling 2 Mini, a multimodal model from Thinking Machines Lab that accepts text and image inputs to generate text outputs\. The model features 24 decoder layers with a looping mechanism where layers 6 to 17 run three times\. It includes a research checkpoint, TML\-d24\-varloop\-research, which supports a variable number of loop passes\.

## Sources

_No safe source URL was recorded._

