Google

company

Verified

AI & ML interests

Google ❤️ Open Source AI

Recent Activity

BalakrishnaCh new activity about 23 hours ago

google/gemma-3-12b-it:Gemma 3 fine tuning max token length

JenJSun updated a model 1 day ago

google/videoprism

BalakrishnaCh new activity 2 days ago

google/gemma-3-1b-it:TRAINING DATA

View all activity

Articles

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

Welcome PaliGemma 2 – New vision language models by Google

PaliGemma – Google's Cutting-Edge Open Vision Language Model

BalakrishnaCh

in google/gemma-3-12b-it about 23 hours ago

Gemma 3 fine tuning max token length

#22 opened about 2 months ago by

JenJSun

updated a model 1 day ago

google/videoprism

Video Classification • Updated 1 day ago • 55

BalakrishnaCh

in google/gemma-3-1b-it 2 days ago

TRAINING DATA

#23 opened 3 days ago by

osanseviero

in google/magenta-realtime 3 days ago

Add `notebook.ipynb` demo to the HF model repo 🤗

#2 opened 3 days ago by

BalakrishnaCh

in google/gemma-3-12b-it-qat-q4_0-gguf 3 days ago

reading Image

#11 opened about 1 month ago by

BalakrishnaCh

in google/gemma-3-27b-it-qat-q4_0-gguf 3 days ago

Image

#12 opened about 1 month ago by

osanseviero

in google/paligemma-3b-pt-896 4 days ago

Import BitsAndBytesConfig in model card snippet

#10 opened 23 days ago by

chrisdonahue-goog

published a model 5 days ago

google/magenta-realtime

Updated 3 days ago • 316

ariG23498

posted an update 22 days ago

Post

1448

🚨 Implement KV Cache from scratch in pure PyTorch. 🚨

We have documented all of our learning while implementing KV Cache to nanoVLM. Joint work with @kashif @lusxvr @andito @pcuenq

Blog: hf.co/blog/kv-cache

1 reply

·

ma-sundermeyer

authored 2 papers 3 months ago

BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation

Paper • 2504.02812 • Published Apr 3 • 5

BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation

Paper • 2504.02812 • Published Apr 3 • 5

GWEfsdf

authored a paper 3 months ago

ShieldGemma 2: Robust and Tractable Image Content Moderation

Paper • 2504.01081 • Published Apr 1 • 3

garyzhao9012

authored a paper 4 months ago

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Paper • 2502.03628 • Published Feb 5 • 12

ariG23498

posted an update 5 months ago

Post

2831

Tried my hand at simplifying the derivations of Direct Preference Optimization.

I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.

Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo

ariG23498

posted an update 5 months ago

Post

2025

Timm ❤️ Transformers

Wtih the latest version of transformers you can now use any timm model with the familiar transformers API.

Blog Post: https://huggingface.co/blog/timm-transformers
Repository with examples: https://github.com/ariG23498/timm-wrapper-examples
Collection: ariG23498/timmwrapper-6777b85f1e8d085d3f1374a1

ariG23498

posted an update 7 months ago

Post

1451

We are blessed with another iteration of Pali Gemma. Google launches PaliGemma 2.

google/paligemma-2-release-67500e1e1dbfdd4dee27ba48

merve/paligemma2-vqav2

ariG23498

posted an update 8 months ago

Post

2973

Qwen/qwen25-66e81a666513e518adb90d9e

Qwen/Qwen2.5-Coder-Artifacts

Qwen/Qwen2.5-Coder-demo

ariG23498

posted an update 8 months ago

Post

1609

Cohere drops two new multilingual models!

https://huggingface.co/CohereForAI/aya-expanse-8b
https://huggingface.co/CohereForAI/aya-expanse-32b

Try them out here

https://huggingface.co/spaces/CohereForAI/aya_expanse

garyzhao9012

authored 2 papers 9 months ago

$ε$-VAE: Denoising as Visual Decoding

Paper • 2410.04081 • Published Oct 5, 2024 • 7

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Paper • 2303.16341 • Published Mar 28, 2023