Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
projectlosangeles 
posted an update 2 days ago
view post
Post
9335
🔥Check out HeartMuLa!!! 🔥

The best open-sourced music generation model in terms of lyrics controllability and music quality!!!

🤗https://huggingface.co/HeartMuLa/HeartMuLa-oss-3B-happy-new-year🤗

❤️Listen to amazing HeartMuLa output samples here:
https://soundcloud.com/aleksandr-sigalov-61/sets/heartmula ❤️

@victor
  • 4 replies
·
ST-x-Tony 
posted an update 1 day ago
view post
Post
4928
Hello everyone,

We are excited to share that SKT-NRS is now live on Hugging Face.
We’ve developed a Neural Reasoning System (NRS) designed to enhance the capabilities of foundation models — giving them stronger reasoning, improved performance, and more reliable outputs across a wide range of tasks.

Our goal is to bring meaningful quality improvements to both new and existing models. You’ll start seeing boosted versions of various models released here soon, each refined with our NRS approach.

**What to Expect* ❤️‍🩹

Regular releases of Neural Reasoning-enhanced models
Clear focus on better reasoning and overall model quality
Ongoing improvements based on community feedback

If you’d like to stay updated, feel free to follow this space — we’ll be posting the first boosted models very soon.

**Community Requests**

Have a specific model you’d like us to work on? Looking for improvements on an existing model, or have any other requests?
We’re happy to hear from you. Please share your suggestions here:

## Community Requests → SKT-NRS/README#1

**Thank you for your support! We look forward to building better models together.**
  • 5 replies
·
sequelbox 
posted an update 3 days ago
view post
Post
7212
NEW RELEASE: Esper 4 is here for Qwen 3.6 27b, along with our new datasets!

- NEW DATASET: Titanium 4 maximizes DevOps and architecture helpfulness, powered by high-difficulty agentic-focused DevOps and architecture data generated with DeepSeek-V4-Pro!
- NEW DATASET: Mitakihara 2 brings AI coding and expertise data for AI development, research, deployment, interpretability, operation and experimentation!
- Improved coding performance: challenging agentic coding queries from Tachibana 4 allow Esper 4 to tackle harder coding tasks across a variety of languages!

GET ESPER 4: ValiantLabs/Qwen3.6-27B-Esper4

Get the datasets for your own training:
sequelbox/Titanium4-DeepSeek-V4-Pro
sequelbox/Mitakihara2-DeepSeek-V4-Pro
sequelbox/Tachibana4-DeepSeek-V4-Pro

We've been working hard on Esper 4 - it's so exciting to finally bring it to everyone! We hope it helps you build.

We'll be expanding Esper 4 to more models as funding allows - donate for more, faster, better models and datasets: sequelbox/SupportOpenSource

The revolution is coming - we're here to fight for AI you can use and build on your own computer, not a giant corporation charging you for access at their discretion. We've seen what OpenAI, Anthropic, and the ultra-rich taking charge of the AI future looks like, and it's already very clear you won't like living in it. Choose a different future while you still can.

Open source must win.

More to come soon!

love, always,
allegra
  • 3 replies
·
AxionLab-official 
posted an update 3 days ago
kanaria007 
posted an update about 8 hours ago
view post
Post
45
✅ Article highlight: *Homeostasis as Goal Tension: Internal State, Stability Bands, and Degrade Triggers* (art-60-182, v0.1)

TL;DR:
This article argues that internal state is not background telemetry.

In embodied SI-Core, low energy, heat, instability, sensor stress, or resource pressure can change what the system should attempt. 182 turns internal state into structured goal tension: bounded pressure that can prioritize, suppress, degrade, or narrow behavior without silently widening authority.

Read:
kanaria007/agi-structural-intelligence-protocols

Why it matters:
• makes internal stress part of route selection, not hidden state
• prevents “I was unstable” from becoming an excuse for wider authority
• defines stability bands that narrow behavior under pressure
• connects homeostasis to jump suppression, safe-mode, and recovery
• gives degradation a receipted structure instead of a vague health flag

What’s inside:
• internal state vectors for typed body/system condition
• homeostatic interpretation records
• tension bands that map stress into bounded goal pressure
• stability policies for posture selection
• suppression records for blocking expensive or unsafe jumps
• degrade-trigger receipts for narrowing action under thresholds
• reentry artifacts that record recovery, posture, and residual limits

Key idea:
Do not say:

*“the system was tired, so it changed behavior.”*

Say:

*“this internal state was parsed into this stability band, emitted this goal tension, triggered this suppression/degrade path, and reentered memory with this recovery posture and receipts.”*

Homeostasis is governance pressure.

Not mood. Not vibes. Not excuse.
laxuu 
posted an update about 12 hours ago
view post
Post
69
Hot take :Wednesday🔥

For years, AI progress has often looked like:

"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.

RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?

Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.

As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:

Are we entering the era where experience becomes more valuable than parameters?

The next breakthrough AI might not be the biggest model.

It might be the one that learns continuously.

📄 Paper: https://arxiv.org/pdf/2505.03238

💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main

#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
DedeProGames 
posted an update 1 day ago
Reubencf 
posted an update 5 days ago
view post
Post
3693
Shadows of Tomorrow is finally live on Hugging Face Spaces with Gradio.

It’s a browser-playable RPG built with Godot, set in a post-nuclear future where players explore Magnus Province, collect medicinal plants, craft medicine, and help cure NPCs.

Play it here: Reubencf/Shadows_of_Tomorrow
  • 10 replies
·
Shrijanagain 
posted an update 20 days ago
view post
Post
203
Excited to launch SKT-ST-X-0-3B by SKT AI Labs! 🚀🇮🇳

​A powerful 3B Parameter Mixture of Experts (MoE) model optimized for high-performance reasoning with a small footprint.


​--> Quick Specs:
> Total Params: ~3B | Active Params: ~1.1B (2 experts/token)
> Pre-trained on 40B tokens (SKT-OMNI-CORPUS-2T)

1.Context: 8K tokens
2.Bilingual: English & Hindi 🇬🇧🇮🇳
3. Base: Built on ST-X-0 with Mixtral stability


​Get 3B intelligence at 1B inference speeds. Fully open-source under Apache-2.0! 👇

​🔗 Try it on Hugging Face: sKT-Ai-Labs/SKT-ST-X-0-3B

​#AI #OpenSource #LLM #MixtureOfExperts #SKTAILabs #MachineLearning
alvarobartt 
posted an update May 22
view post
Post
399
Open agents on AWS SageMaker AI with open models from the Hugging Face Hub!

> Deploy an open model from the Hugging Face Hub on SageMaker AI
> Connect the deployed model to Strands Agents
> Add built-in and custom tools for tool calling
> Expose external capabilities through MCP integration
> Bonus: talk to your agent and visualize traces with Gradio

https://alvarobartt.com/agents-on-aws-sagemaker
Recently active users