Open-Source AI Meetup

community

Activity Feed Request to join this org

AI & ML interests

Open science and open source

Recent Activity

shahrukhx01 authored a paper about 1 month ago

Transformers for molecular property prediction: Domain adaptation efficiently improves performance

pandeyps authored a paper 4 months ago

KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs

MaximumEntropy authored a paper 6 months ago

Ministral 3

View all activity

jeffboudier

posted an update 23 days ago

Post

235

@alvarobartt published a step-by-step guide to deploy zai-org/GLM-5.2 on AMD GPUs, using newly released features in Microsoft Foundry. The FP8 model fits on a single node of MI300X GPUs, which cuts the bill in half vs. H100.

https://alvarobartt.com/goal-glm-5.2-on-foundry/

spillai

posted an update 2 months ago

Post

8778

mm-ctx – fast, multimodal context for agents.

LLM-based agents handle text incredibly well, but images, videos, or PDFs with visual content are hard to interpret. mm-ctx gives your CLI agent multi-modal skills.

Try it interactively in Spaces: vlm-run/mm-ctx

Readme: https://vlm-run.github.io/mm/
PyPI: https://pypi.org/project/mm-ctx
SKILL.md: https://github.com/vlm-run/skills/blob/main/skills/mm-cli-skill/SKILL.md

mm-ctx is meant to feel familiar: the UNIX tools we already love (find/cat/grep/wc), rebuilt for file types LLMs can't read natively and designed to work with agents via the CLI.
- mm grep "invoice #1234" ~/Downloads searches across PDFs and returns line-numbered matches
- mm cat <document>.pdf returns a metadata description of the file
- mm cat <photo>.jpg returns a caption of the photo
- mm cat <video>.mp4 returns a caption of the video

A few things we obsessed over:
⚡ Speed: Rust core for the hot paths
🏠 Local-first, BYO model: Uses any OpenAI-compatible endpoint: Ollama, vLLM/SGLang, LMStudio with any multimodal LLM (Gemma4, Qwen3.5, GLM-4.6V).
🔗 Composable: stdin + structured outputs
🤖 Drops into any agent via mm-cli-skills: Claude Code, Codex, Gemini CLI, OpenClaw.

We’d love to hear your feedback! Especially on the CLI and what file types and workflows you would like to see next.

2 replies

Keeby-smilyai

posted an update 4 months ago

Post

3178

Hello everyone!

1 reply

jorgemunozl

posted an update 6 months ago

Post

483

just published a short article about something that bit me hard while porting PI05’s subtask prediction to PyTorch: left vs right alignment in transformer padding.
turns out JAX (what Physical Intelligence used) and Hugging Face use opposite padding conventions — and if you don’t catch it, your model silently produces nonsense instead of crashing. no NaN, no error, just garbled subtasks 🤡
i walk through the full tensor pipeline — images → embeddings → pad masks → attention masks → position IDs — and show exactly where the mismatch corrupts everything. also included the implementation file with the fix.
if you’ve ever ported a model between frameworks or messed with custom attention patterns, i think you will enjoy it

1 reply

himanshubeniwal

authored 6 papers 10 months ago

Cross-lingual Editing in Multilingual Language Models

Paper • 2401.10521 • Published Jan 19, 2024 • 2

Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Models

Paper • 2402.11997 • Published Feb 19, 2024 • 1

Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs

Paper • 2502.16901 • Published Feb 24, 2025

COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing

Paper • 2503.21670 • Published Mar 27, 2025

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages

Paper • 2504.04377 • Published Apr 6, 2025 • 1

COMMENTATOR: A Code-mixed Multilingual Text Annotation Framework

Paper • 2408.03125 • Published Aug 6, 2024

Teja-Gollapudi

authored 3 papers 10 months ago

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Paper • 2509.25760 • Published Sep 30, 2025 • 56

The Unreasonable Effectiveness of Eccentric Automatic Prompts

Paper • 2402.10949 • Published Feb 9, 2024 • 5

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning

Paper • 2507.18857 • Published Jul 25, 2025 • 2

jeffboudier

posted an update 11 months ago

Post

3450

Quick 30s demo of the new Hub > Azure AI integration to deploy HF models in your own Azure account. Now with Py and CLI!

GG @alvarobartt @kramp @pagezyhf

merterbak

posted an update 12 months ago

Post

5545

OpenAI is now open again! Check out OpenAI’s brand new gpt‑oss‑20b model hosted on ZeroGPU 🤗

merterbak/gpt-oss-20b-demo

jeffboudier