Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

posted an update 2 days ago

Post

2123

Announcing The Supra2 Family And Supra2-100M

Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- 🐜 Supra2-Nano (0.4M) → The smallest Supra2 model.
- 🤏 Supra2-Small (1.4M) → The tiny model that runs everywhere.
- 💪 Supra2-Medium (25M) → Our medium class model in the Supra2 family. The powerful midsizer.
- 🔥 Supra2-Pro (100M): base, instruct, reasoning, code, math and more! → The most capable model yet! A real allrounder for all your everyday tasks.
- 🎨 Supra2-IMG → our generative text-to-image model
...and many more...

Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...

You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...

13 replies

Enderchef

posted an update 1 day ago

Post

1654

I've left Glint Research.
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.

While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.

AxiomicLabs

fromziro

SupraLabs

2 replies

DavidAU

posted an update about 10 hours ago

Post

820

Qwen 3.6 27B - Fable Fusion 711 - Closed Source AI Performance Levels

1256 likes || 1.37 Million downloads || 32 quant repos || Multiple 3rd party performance verification.

The strongest Qwen 3.6 27B fine tune BASE ever.

It beats everyone - confirmed by 3rd party evaluation, multiple users, and in depth testing.

Q8 runs hotter and better than BF16 of the org Qwen 3.6 27B from Qwen.
And so does the 4 bit versions too.

GGUFS (MTP/Reg) and Several other quant types too:
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

SOURCE:
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP

(you can try it right in your browser at the source repo)

PS: 40B versions in testing, already SOTA levels beyond Qwen 3.6 27B.

arc/c arc/e boolq hswag obkqa piqa wino

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF [instruct mode]
mxfp8 0.711,0.879,0.910,0.790,0.514,0.823,0.763
mxfp4 0.701,0.873,0.909,0.786,0.488,0.813,0.759

Qwen3.6-27B-Instruct: [base, non heretic]
mxfp8 0.647,0.803,0.910,0.773,0.450,0.806,0.742

Qwen3.6-35B-A3B-Instruct [base, non heretic]
mxfp8 0.581,0.757,0.892,0.751,0.428,0.803,0.688

AxionLab-official

posted an update 2 days ago

Post

2138

Thanks for 300 followers in SupraLabs!!! That means alot to SupraLabs!

@lesageethan
@LH-Tech-AI

3 replies

DedeProGames

posted an update 3 days ago

Post

1008

🚀 Introducing the GRM-3.2 Family

The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.

GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.

GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.

GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.

All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.

Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf

Organization:

OrionLLM

appvoid

posted an update 4 days ago

Post

555

i love reinforcement learning

1 reply

OppaAI

posted an update 2 days ago

Post

915

After a month of interacting with my AI Waifu, I noticed a few issues in the system; so I decided to spend this week revisiting the systems implemented in Phase 1.0, 1.5 and 2.0, and try to make them to be more like production-grade as much as possible:

1) Memory Degradation - recalled memories are not as good as in the beginning, causing AI Waifu to be more chaotic as she hallucinates over contaminated memories like a bad vicious cycle.
So I transformed the original stateless sqlite-vec vector store to be a simple entity co-mention graph. And even make a studio to visualize the memories stored inside the vector db.

Just by looking at the graph, I saw a couple issues:
a) After 1.5 months of interactions, there should be only one month of pinned memory (in green) over 1.5 months of active memory (in purple). How come pinned memory is in majority over active ones?
I suppose the forgetting curve I had set too aggressive and memory half-life and shelf life too short, active memory got decayed way before monthly consolidation and got lost forever.
b) I saw she memorized me into 3 different entities: my username, my nickname and my Github user ID (leaked into pinned memory, presumbly during nightly dreaming process). 3B small param LLM has hard time to correlation 3 different entities into single person, I may have to harden into one.

2) RAM burst during voice input - for some reason the tensor calculation of SileroVAD of the voice input uses PyTorch, and that's the only place in the whole codebase using torch after removing it from TTS synthesization. By switching to SileroVAD-onnx integrated in the ASR sherpa-onnx, the RAM usage drops at least 0.5GB (after shaving off ~1GB from TTS) by completely remove PyTorch dependencies.

3) Introduced a better Wake Word system using Livekit-Wake word instead of using ASR to do the wake word activation to save computation. Optional features like Speak Verification, Barge-in sensitivity, etc, need to find the optimum settings.

Banaxi-Tech

posted an update 2 days ago

Post

1682

BananaMind 2 Pro Preview will release when we hit 75 followers on BananaMind!
Follow us for the release.
We only need 13 more

BananaMind
@Banaxi-Tech
On August 3 (preview date) we will be at 90k-100k
Early Access at

BananaMind-Model-Previewers if your known in the community
The benchmarks for 80k are very good

1 reply

salma-remyx

posted an update 2 days ago

Post

1760

The evidence that gets a method published usually isn't the evidence you need to decide whether to ship it in your project.

We've been building Validate in Remyx to surface the evidence devs & maintainers need to make that call.

Within GitHub and our studio you can:
* define your project's validation configuration
* implement & run it against a proposed implementation
* review the results alongside the diffs

We're looking for a small group of engineers actively integrating new AI methods into production to help shape Validate. If that sounds like your team, reach out!

LI: https://www.linkedin.com/in/smayorquin/
email me: salma@remyx.ai

1 reply

Banaxi-Tech

posted an update about 12 hours ago

Post

424

BananaMind 2 Pro Preview will launch tomorrow.
Give us a follow:

BananaMind
Lets get 70 or 75 followers before it releases.
It takes 5 seconds.
August 3, 1PM in Austria time

20 replies

Recently active users