Hugging Face (Twitter)

RT @dylan_ebert_: I automated my research discovery.

Claude Code + Hugging Face MCP + Research MCP (my server)

It makes discovering and keeping track of all related research artifacts MUCH faster and easier

here's how it works 👇

‌Hugging Face (Twitter)

RT @arundhati1504: 🎉 Introducing Granary — a 1M-hour, open multilingual speech dataset — plus new #opensource ASR models. 🌍
.
🤗 Now on HuggingFace: nvda.ws/3Jg0BwV

🔗 Learn more: nvda.ws/41DVP2s bit.ly/4mGyMMA

‌Hugging Face (Twitter)

RT @AdinaYakup: Before my vacation: Qwen releasing.
When I came back: Qwen still releasing
Respect!!🫡

Meet Qwen Image Edit 🔥 the image editing version of Qwen-Image by @Alibaba_Qwen
https://huggingface.co/Qwen/Qwen-Image-Edit

✨ Apache 2.0
✨ Semantic + Appearance Editing: rotate, restyle, add/remove 🎨
✨ Precise Text Editing → edit CN/EN text, keep style

‌Hugging Face (Twitter)

RT @VentureBeat: Nvidia releases a new small, open model Nemotron-Nano-9B-v2 with toggle on/off reasoning

‌Hugging Face (Twitter)

RT @ClementDelangue: Do we have an org or posts with all the cool Japanese releases on HF? Which ones are the most interesting ones?

Hugging Face (Twitter)

RT @gm8xx8: NVIDIA Nemotron-Nano v2

Models: 12B Base, 9B Reasoning, 9B Base
- Arch: Hybrid Mamba2–Transformer (128K ctx, 4 attn layers)
- Training: 10.6T tokens (3.5T synthetic from DeepSeek, Qwen, Nemotron-4, phi-4, etc.)
- 15 natural languages + 43 programming languages
- Datasets: Nemotron-CC v2 + Nemotron-CC-Math (133B tokens, 5.5× FineMath)

Benchmarks
- Math: 91.4 GSM8K CoT, 63.6 MATH L5, +30→56.7 AIME
- Code: 58.5 HumanEval+, 58.9 MBPP+
- Commonsense: 90.7 ARC, 79.9 HellaSwag
- Long-context: 82.2 RULER-128K

Highlights
- Nemotron-CC-Math: First scalable pipeline using Lynx + LLM cleanup to preserve LaTeX + code in web data. Delivers SOTA boosts (+12.6 MATH, +14.3 MBPP+) vs prior open math sets
- Efficiency: Distilled 12B→9B (480B tokens), ~1.5e24 FLOPs, ~724 MWh disclosed
- Deployment: Hugging Face, NGC, NeMo, TRT-LLM, vLLM | GPU-optimized
- Open: Models, datasets, and full extraction pipelines released

Hugging Face (Twitter)

RT @ctnzr: Today we're releasing NVIDIA Nemotron Nano v2 - a 9B hybrid SSM that is 6X faster than similarly sized models, while also being more accurate.

Along with this model, we are also releasing most of the data we used to create it, including the pretraining corpus.

Links to the models, datasets, and tech report are here:

https://research.nvidia.com/labs/adlr/NVIDIA-Nemotron-Nano-2/

Hugging Face (Twitter)

RT @NielsRogge: Ok ngl this is cool! The end of LoRa's??

Powered by @FAL as inference provider. Try it out below! https://twitter.com/Alibaba_Qwen/status/1957500569029079083#m

Hugging Face (Twitter)

RT @maximelabonne: LFM2-VL support with GGUF and llama.cpp 🥳

You can now run these tiny, hyper-efficient VLMs on your watch!

We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface

Hugging Face (Twitter)

RT @multimodalart: IT'S OUT! 🚀 MoDA: Multi-modal Diffusion Architecture for Talking Head Generation

finally a talking head:
open source 🏋️
fast ⚡
portrait + audio-driven 🧑‍🎨🎧
with emotion control

(and yes, i built an inference system + Gradio, generate in < 15s on @huggingface spaces 🤗)

‌Hugging Face (Twitter)

RT @HaihaoShen: GLMs:
https://huggingface.co/Intel/GLM-4.5-gguf-q2ks-mixed-AutoRound
https://huggingface.co/Intel/GLM-4.5V-int4-AutoRound
#intel #autoround @thukeg

Hugging Face (Twitter)

RT @Xianbao_QIAN: nano-banana, qwen-image-edit, what else?

Try @StepFun_ai NextStep-1-Large-Edit

- 14B AR model
- Apache 2 license
- Demo available on @huggingface
- Pretrain model also made available

Link below

‌Hugging Face (Twitter)

RT @reach_vb: WE ARE SO BACK!!!

https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base

‌Hugging Face (Twitter)

RT @_akhaliq: DeepSeek-V3.1
https://huggingface.co/collections/deepseek-ai/deepseek-v31-68a491bed32bd77e7fca048f

Hugging Face (Twitter)

RT @allen_ai: We’re releasing early pre-training checkpoints for OLMo-2-1B to help study how LLM capabilities emerge. They’re fine-grained snapshots intended for analysis, reproduction, and comparison. 🧵

Hugging Face (Twitter)

RT @RisingSayak: It's out friends!

Really great to see the state of things in image edits, video fidelity being pushed further and further, thanks to the community!

This release also features new fine-tuning scripts for Qwen-Image and Flux Kontext (with support for image inputs). So, get busy making these models your own 🤗

We also improved the loading speed of Diffusers pipelines & models. This will become particularly evident when operating with large models like Wan, Qwen, etc.

Release notes: https://github.com/huggingface/diffusers/releases/tag/v0.35.0

Hugging Face (Twitter)

RT @ClementDelangue: Deepseek just released a new model! https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base

Hugging Face (Twitter)

RT @dylan_ebert_: OmniPart: Part-Aware 3D Generation

🪛 Semantic decoupling
🏙️ Structural cohesion
🤗 Free and open source

demo available on Hugging Face

Hugging Face (Twitter)

RT @Alibaba_Qwen: Thank you! Qwen-Image-Edit is now available in anycoder! https://twitter.com/_akhaliq/status/1957519569016238268#m