Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
danielhanchen 
posted an update 1 day ago
view post
Post
3399
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀

Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing

Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
bartowski 
posted an update 2 days ago
view post
Post
4277
You may have noticed that my upload of MiMo-V2.5 upload didn't have the author in the model name:

bartowski/MiMo-V2.5-GGUF

Going forward, I plan to upload models from major 1st party developers without the author name attached for cleanliness, I feel it results in a nicer and more expected user experience

I will continue to uploaded fine tunes with that author + "_" appended for clarity, I personally feel it's nice to know at a glance who's tune it is, but it's also for the reason I first started doing it, to avoid it being confused for a new version of the official release

I hope this change makes sense, it seemed most reasonable to me and a poll I did (forever ago, I move slow sometimes) made it seem likely others would find it reasonable as well (feel free to let me know if you disagree, may not change my mind but I do value knowing what others think)

Thanks for downloading :)
  • 1 reply
·
DedeProGames 
posted an update 2 days ago
view post
Post
4880
🚀 Introducing the GRM-2.6 Family

The GRM-2.6 family is a new generation of reasoning-focused models from Orion LLM Labs, built for difficult tasks, coding, STEM, terminal agents, and advanced local AI workflows.

GRM-2.6-Plus is the main high-capability model in the family: a 27B-class reasoning model based on Qwen3.6, designed for strong structured reasoning, coding, agentic use, and practical local deployment.

GRM-2.6-Opus builds on GRM-2.6-Plus as a merge with an Opus-style reasoning distilled model, improving structured reasoning behavior, terminal-agent workflows, coding ability, and complex problem solving.

Both models are designed for users who want powerful reasoning models that remain practical for research, local inference, coding, and agent experiments.

Models:
GRM-2.6-Plus: OrionLLM/GRM-2.6-Plus
GRM-2.6-Opus: OrionLLM/GRM-2.6-Opus

Organization:
OrionLLM
  • 1 reply
·
tifischer 
posted an update 2 days ago
view post
Post
616
I created a model using a notebook and am happy with its accuracy. The next step was to deploy it on huggingface space and use api to submit a form that executes the model on the backend.

My files are uploaded. My front end look good. By Backend health check is good. The space is running with no errors. However, when I submit the predict button the app just times out waiting for the backend to respond. THere are no errors in the logs. but the front end reponds API Error 500. If I switch to dev mode which I understand is in preview then the build breaks, so I cannot use that.

tifischer/SmartKart_Prediction
unmodeled-tyler 
posted an update 2 days ago
view post
Post
2906
Just started a fun project!

unmodeled-tyler/DoW-UFO-UAP-1

I'm getting the recently released DoW UFO/UAP documents (https://war.gov/ufo) cleaned and converted into a dataset here on Hugging Face!

There 161 different files in the gov release (pdfs, images, videos, audio, etc) and my current plan is to do it all in 1 dataset with 4 different shards - that way you can just call whichever tables you want/need when you import the dataset.

This is an ongoing project (I'm doing it on the side + my regular projects) so it's a bit of a growing entity. I'll also continuously refine the data over time to make sure it's as clean as possible.

Check it out! Who knows what you'll find in there?
  • 2 replies
·
mipo57 
posted an update 3 days ago
kanaria007 
posted an update 1 day ago
view post
Post
125
✅ Article highlight: *LLM Wrappers as Proposal Engines, Not Authorities* (art-60-232, v0.1)

TL;DR:
This article argues that LLM wrappers should not hold runtime authority.

A wrapper may draft proposals, but it should not directly own world-facing effect power. In SI-style migration, the wrapper produces a proposal under a declared wrapper profile, that draft is parsed under a governed contract, parse failures are handled explicitly, gates evaluate the parsed proposal, and only then can runtime authority decide whether any effect is admissible.

Read:
kanaria007/agi-structural-intelligence-protocols

Why it matters:
• separates model suggestion from runtime authority
• makes parse failure a governed event instead of a silent fallback
• gives legacy LLM-agent stacks a realistic migration path without pretending the wrapper is already safe
• keeps effect-ledger discipline and runtime gating in the authority layer, not in the model shell

What’s inside:
• wrapper profiles as bounded proposal-generation contracts
• proposal drafts, parsed jump receipts, and jump outcome records
• governed handling for parse failure, partial parse, and draft rejection
• gates that evaluate parsed proposals before any live effect path opens
• the rule that effects execute under runtime authority and effect-ledger discipline, not under model autonomy

Key idea:
Do not say:

*“the agent decided and used tools.”*

Say:

*“the wrapper proposed, the proposal was parsed or failed under a governed contract, gates evaluated it, and any resulting effect was executed under runtime authority.”*
sergiopaniego 
posted an update 2 days ago
view post
Post
1562
OpenEnv is growing fast in tutorials. If you're looking to get started with RL environments, check them out

> evaluate your agents using OpenEnv
> learn how rewards work via rubrics
> connect agents via MCP
> many moreeeee!

anything you think it's missing?

https://meta-pytorch.org/OpenEnv/tutorials/index.html
Kseniase 
posted an update May 25, 2025
view post
Post
8171
12 Types of JEPA

JEPA, or Joint Embedding Predictive Architecture, is an approach to building AI models introduced by Yann LeCun. It differs from transformers by predicting the representation of a missing or future part of the input, rather than the next token or pixel. This encourages conceptual understanding, not just low-level pattern matching. So JEPA allows teaching AI to reason abstractly.

Here are 12 types of JEPA you should know about:

1. I-JEPA -> Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (2301.08243)
A non-generative, self-supervised learning framework designed for processing images. It works by masking parts of the images and then trying to predict those masked parts

2. MC-JEPA -> MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features (2307.12698)
Simultaneously interprets video data - dynamic elements (motion) and static details (content) - using a shared encoder

3. V-JEPA -> Revisiting Feature Prediction for Learning Visual Representations from Video (2404.08471)
Presents vision models trained by predicting future video features, without pretrained image encoders, text, negative sampling, or reconstruction

4. UI-JEPA -> UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity (2409.04081)
Masks unlabeled UI sequences to learn abstract embeddings, then adds a fine-tuned LLM decoder for intent prediction.

5. Audio-based JEPA (A-JEPA) -> A-JEPA: Joint-Embedding Predictive Architecture Can Listen (2311.15830)
Masks spectrogram patches with a curriculum, encodes them, and predicts hidden representations.

6. S-JEPA -> S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention (2403.11772)
Signal-JEPA is used in EEG analysis. It adds a spatial block-masking scheme and three lightweight downstream classifiers

7. TI-JEPA -> TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems (2503.06380)
Text-Image JEPA uses self-supervised, energy-based pre-training to map text and images into a shared embedding space, improving cross-modal transfer to downstream tasks

Find more types below 👇

Also, explore the basics of JEPA in our article: https://www.turingpost.com/p/jepa

If you liked it, subscribe to the Turing Post: https://www.turingpost.com/subscribe
  • 1 reply
·
MidasRev 
posted an update about 20 hours ago
view post
Post
65
I would like to know with that spec what the best AI to use for coding

NVIDIA A10 24GO gddr6
AMD EPYC7313p
128Go ddr4ecc

Thanks to ppl who gonna help bcs i cant found a fast enought all 31b models are slow even the idk what to do or config if someone can send me the config too thx !
  • 6 replies
·
Recently active users