OPEN SOURCE - AI Dynamics

Qwen3-235B-A22B-2507 released with performance boost

By

–

21 July 2025 21h56

Qwen released Qwen3-235B-A22B-2507, a minor upgrade to Qwen3-235B-A22B, which provides a significant performance boost. Already available on Qwen chat

→ View original post on X — @testingcatalog

21 July 2025

Building Transformers.js App with Kimi K2 and Groq

By

@_akhaliq

–

21 July 2025 17h17

Kimi K2 + @GroqInc vibe coding in anycoder build a transformers.js app for Xenova/moondream2 model card info and example included in prompt app was deployed successfully on HF in one click

→ View original post on X — @_akhaliq

21 July 2025

Mono-InternVL-1.5: Efficient Monolithic Multimodal Language Models

By

@_akhaliq

–

21 July 2025 15h48

Mono-InternVL-1.5 Towards Cheaper and Faster Monolithic Multimodal Large Language Models

→ View original post on X — @_akhaliq

21 July 2025

Agentic Doc: Python Library for Document Data Extraction

By

@sumanth_077

–

20 July 2025 16h19

Turn documents into LLM-ready data! Agentic Doc is a Python library for agentic document extraction. It pulls structured data from visually complex documents like tables, images, and charts and returns a hierarchical JSON with exact element locations. 100% Open Source

→ View original post on X — @sumanth_077

20 July 2025

ChatGPT Router Behavior Change Noticed

By

@testingcatalog

–

20 July 2025 15h33

I feel like ChatGPT router already acts differently (dunno since when). Responses to non existing models (edge cases?) are handled by the model or router model with a slightly different system prompt. * model name changed for testing purposes only

→ View original post on X — @testingcatalog

20 July 2025

Comparing Local LLM Sizes to Wikipedia Dumps

By

@simonw

–

19 July 2025 23h16

Evan Hahn made this handy table comparing the size of different LLMs to the size of Wikipedia dumps in various shapes and formats https://
evanhahn.com/local-llms-ver
sus-offline-wikipedia/
…

→ View original post on X — @simonw

19 July 2025