ariG23498 (Aritra Roy Gosthipaty)

reacted to mrfakename's post with 🔥 about 1 month ago

Post

5251

Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.

Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.

Will probably kick off a new run later with some settings tweaked.

Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo

(Turn 🔊 on to hear audio samples)

4 replies

·

reacted to sergiopaniego's post with 🔥 about 1 month ago

Post

1963

New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.

You can compare how models reason about images 🧠

Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.

Let’s gooo

sergiopaniego/vlm_object_understanding

reacted to tsungyi's post with 🔥 2 months ago

Post

3689

We’re excited to share that Cosmos Reason has surpassed 1 million downloads on Hugging Face!

Cosmos Reason is an open, customizable, commercial-ready 7B-parameter reasoning vision language model (VLM) designed for physical AI. By combining physics understanding, prior knowledge, and common sense reasoning, Cosmos Reason empowers AI agents and robots to operate intelligently in real-world environments.

Key applications already unlocked include:

✅ Automating large-scale dataset curation and annotation

🤖 Powering robot planning and vision-language action (VLA) decision-making

📊 Driving advanced video analytics and actionable insight generation

We’re proud to see a global community of developers using Cosmos Reason to teach robots to think like humans—and we’re just getting started.

⚡ Get started with Cosmos Reason 1 NIM, an easy-to-use microservice for AI model deployment: https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/cosmos-reason1-7b?version=1

📈 See the leaderboard: facebook/physical_reasoning_leaderboard

reacted to lysandre's post with 🔥👍🚀 3 months ago

Post

6876

We're kick-starting the process of Transformers v5, with @ArthurZ and @cyrilvallez !

v5 should be significant: we're using it as a milestone for performance optimizations, saner defaults, and a much cleaner code base worthy of 2025.

Fun fact: v4.0.0-rc-1 came out on Nov 19, 2020, nearly five years ago!

6 replies

·

reacted to sergiopaniego's post with 🧠🧠 3 months ago

Post

4317

gpt-oss was possible thanks to new engineering efforts in 🤗 transformers. We just dropped a blog covering them:

- Kernels from the Hub
- MXFP4 Quantization
- Tensor & Expert Parallelism
- Dynamic Sliding Window & Cache
- Continuous Batching & Paged Attention

Grab a coffee & dive in! ☕️

https://huggingface.co/blog/faster-transformers

replied to their post 3 months ago

hf.co/blog/faster-transformers

posted an update 3 months ago

Post

1135

New post is live!

This time we cover some major updates to transformers.

🤗

1 reply

·

posted an update 4 months ago

Post

874

I have always advocated for writing techinical stories without using LLMs.

The following one page editorial really drives the point home.
https://www.nature.com/articles/s44222-025-00323-4

reacted to jsulz's post with 🔥🤯🚀 5 months ago

Post

3280

We've moved over 20PB from Git LFS to Xet on the Hub without downtime or data loss. Having things "just work" on a migration of this scale is about as good as it gets.

Now, we're migrating the rest of the Hub https://huggingface.co/blog/migrating-the-hub-to-xet

But how did we get here?

In the early days of joining Hugging Face, we made a few key design decisions:
* There would be no "hard cut-over" from Git LFS to Xet
* A Xet-enabled repository should be able to contain both Xet and LFS files
* Repository migrations from LFS to Xet can run in the background without disrupting downloads or uploads

These were largely driven by our desire to ensure the community could keep working without interruption.

We cover the infrastructure making this all go in this post, specifically:
* An integral piece of infrastructure known internally as the Git LFS Bridge
* Background content migrations that run around the clock

To skip the wait and join Xet now, sign up here https://huggingface.co/join/xet

posted an update 6 months ago

Post

1736

🚨 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

·

reacted to danielhanchen's post with 🔥 6 months ago

Post

3839

New DeepSeek-R1-0528 1.65-bit Dynamic GGUF!

Run the model locally even easier! Will fit on a 192GB Macbook and run at 7 tokens/s.

DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-GGUF
Qwen3-8B DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

And read our Guide: https://docs.unsloth.ai/basics/deepseek-r1-0528

reacted to hesamation's post with 🔥 6 months ago

Post

2794

I really like how this seven-stage pipeline was laid out in the Ultimate Guide to Fine-Tuning book.

It gives an overview, then goes into detail for each stage, even providing best practices.

It’s 115 pages on arxiv, definitely worth a read.

Check it out: https://arxiv.org/abs/2408.13296

reacted to merve's post with 🔥 7 months ago

Post

5098

VLMS 2025 UPDATE 🔥

We just shipped a blog on everything latest on vision language models, including
🤖 GUI agents, agentic VLMs, omni models
📑 multimodal RAG
⏯️ video LMs
🤏🏻 smol models
..and more! https://huggingface.co/blog/vlms-2025

1 reply

·

reacted to merve's post with 👍🚀 7 months ago

Post

6702

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥

D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩

> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352

Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩

Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️

D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩

Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️

this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

2 replies

·

Aritra Roy Gosthipaty PRO

AI & ML interests

Recent Activity

Organizations

Aritra Roy Gosthipaty PRO

AI & ML interests

Recent Activity

Organizations

ariG23498's activity