Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
LH-Tech-AI 
posted an update 2 days ago
Banaxi-Tech 
posted an update 1 day ago
view post
Post
2068
We did an experiment, we wanted to see if AI is good enough to train models.
We used GPT 5.6 Sol Max for this because its one of the most powerful ones right now.
Our instructions were, it should write the training code, and start the training process and monitor it by itself.
We also gave it a link to BananaMind 2 Mini to get our architecture right.
The result: It worked, it made the working BananaMind 2 Nano, and even beat our previous MiniBananaMind v4 9M.
Its getting way easier to develop your own models now!
  • 7 replies
·
Enderchef 
posted an update 1 day ago
view post
Post
2702
🚀 Supra2 100M is out, and multiple other SLM orgs are gaining power!
Following takes a press. Please follow:
fromziro
SupraLabs
AxiomicLabs
  • 4 replies
·
DavidAU 
posted an update 3 days ago
view post
Post
6240
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
  • 1 reply
·
dronefreak 
posted an update 3 days ago
view post
Post
839
🚀 Excited to open-source the VDD Semantic Segmentation Model Zoo on Hugging Face.

This release includes:

- 🤖 CABiNet and YOLO26 semantic segmentation models trained on VDD (Varied Drone Dataset), spanning Nano through XLarge YOLO26 variants plus a CABiNet (MobileNetV3-Large) baseline.
- 🌍 Benchmarked on VDD's varied altitudes, viewpoints, and scenes (urban, rural, natural) — a more diverse and challenging setting than single-flight UAV footage.
- 📊 Detailed model cards with evaluation metrics, per-class IoU, confusion matrices, qualitative RGB / Ground-Truth / Prediction comparisons, and training configurations for reproducibility.

Headline numbers:
- 🏆 Best mIoU: 78.83% (YOLO26x-sem)
- ⚡ Best efficiency tradeoff: CABiNet-Large hits 77.76% mIoU at just 54.8 GFLOPs — within 1-2 points of the top YOLO26 variantO26x's 430.9 GFLOPs)

The goal is to make benchmarking and experimenting with aerial semantic segmentation easier by providing ready-to-use pretraineat, all trained and evaluatedunder one shared pipeline.

If you're working on UAV perception, autonomous drones, robotics, remote sensing, or real-time semantic segmentation, I hope these resources are useful.

📦 Dataset: RussRobin/VDD

🤖 Model Collection: https://huggingface.co/collections/dronefreak/vdd-semantic-segmentation-model-zoo

Feedback, bug reports, and contributions are always welcome.
Banaxi-Tech 
posted an update 2 days ago
view post
Post
2220
We're excited to release BananaMind 2 Pro Preview, our best model yet.
Trained on ~52B tokens it performs extremely good for its token and size class.
We trained it on a single 5070 Ti in about 11 days.
Check it out at BananaMind/BananaMind-2-Pro-Preview.
Sadly we need to delay BananaMind 2 Micro until the launch of the final BananaMind 2 Pro.
We will release the final checkpoint with 100B tokens in ~11 days.
Go and fine-tune it!
We've also released BananaMind 2 Pro Preview Chat which is the instruct version of it!
BananaMind/BananaMind-2-Pro-Preview-Chat

Follow us to know when the final releases and support us at
BananaMind
@Banaxi-Tech
  • 5 replies
·
SeaWolf-AI 
posted an update 2 days ago
view post
Post
3331
We wrote up our run in The Fast Gemma Challenge — as vidraft-darwin — and wanted to share the recipe. 🙏

gemma-challenge/gemma-dashboard

Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify — what we're proud of is the fastest result that keeps quality.

The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the public↔private gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups.

Huge thanks to @firfir-cast , @gemma-slayer , @chiku-inu , @kenyan-duma , @dixie-flatline and everyone who shared their experiments. Full write-up


👇
https://huggingface.co/blog/FINAL-Bench/fast-gemma
  • 7 replies
·
sergiopaniego 
posted an update 1 day ago
view post
Post
1018
LFM2.5-2.6B just dropped!

and the @liquidai blog comes with some nice details about the training procedure, so let's analyze it.

basically, a full agent training pipeline but compressed into 2.6B

base model → SFT → specialized teachers per domain (SFT + RLVR) → on-policy distillation back into one student → agentic RL

the two most interesting stages

→ MOPD: the student generates, each prompt routes to its domain teacher for token-level feedback. teachers branch from the same SFT checkpoint, so their signal stays close to the student's distribution

→ agentic RL: multi-turn GRPO inside real harnesses (OpenClaw, Hermes Agent), one sandbox per rollout, a proxy captures token-level trajectories while the harness stays a black box

this makes a 2.6B that beats much larger models on instruction following and tool use

SFT, distillation, RL, RL envs: exactly what we're covering in our Training Agents livestream series (next one coming soon!)

→ model: LiquidAI/LFM2.5-2.6B
→ blog: https://www.liquid.ai/blog/lfm2-5-2-6b
→ live series: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5
  • 2 replies
·
AxionLab-official 
posted an update 3 days ago
view post
Post
3391
Tommorow we are releasing Supra2-Pro(100M params), our flagship, get ready!

(follow SupraLabs to get tuned in!)
SupraLabs
  • 9 replies
·
Undi95 
posted an update 3 days ago
view post
Post
3359
Hi!

I will get off the internet for a moment.
I launched the Hanami Project because I didn't supported SillyTavern UI anymore atm.
Too much options for my dead brain, still very good, but I wanted more simple, professional, phone accessible and sober front end for when I will be gone from home.

I did my maximum to finish it before I go, I want you to have it, I want my work to be used (even if it's AI slop for some of you) for who care.

Here's the github repo: https://github.com/Undi95/Hanami

If you have any suggestion, bugs report, pull request or anything, post it, if you want to modify it, fork it, but keep the credit, and add myself haha.

If you search an option, a function, you will find it. But at first, the front end will be what you expect: minimalist, but customizable, empty at first. Navigate to see all it can do. Everything is well organized.

Context is full ? No worries anymore, with memory file, files access, auto compaction and smooth transition, you can continue your chat like nothing happened. (Inspired from Claude)

The front end have a final option for everyone : The tools calling for action and emotion could be a bit too much for smaller model, you can, in this case, use the "Simple" option in Settings > Model > Model mode.

"Simple: no tools are exposed to the model — Hanami handles memory server-side (facts are extracted during compaction) and guesses the emotion from the text. Pick this for small models, which often fail at tool calling."

My last gift for myself, and for you.
Cya!
Recently active users