gg-hf-gm (gg-hf-gm)

posted an update 1 day ago

Post

182

One of my favorite perks of the Hugging Face Pro plan: ✨Dev mode✨

Connect your HF Space to VS Code and just build — with hot reload out of the box.

Game changer for fast prototyping. 💻

Google Colab made AI accessible. Now HF Spaces are doing it too! 😍

💡 New Hugging Face pricing: http://hf.co/pricing
💡 More details: https://huggingface.co/learn/cookbook/en/enterprise_cookbook_dev_spaces

danielhanchen

posted an update 7 days ago

Post

450

We updated lots of our GGUFs and uploaded many new ones!
* unsloth/dots.llm1.inst-GGUF
* unsloth/Jan-nano-GGUF
* unsloth/Nanonets-OCR-s-GGUF
* Updated and fixed Q8_0 upload for unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
* Added Q2_K_XL for unsloth/DeepSeek-R1-0528-GGUF
* Updated and fixed Vision support for unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF

reach-vb

posted an update 12 days ago

Post

2074

Excited to onboard FeatherlessAI on Hugging Face as an Inference Provider - they bring a fleet of 6,700+ LLMs on-demand on the Hugging Face Hub 🤯

Starting today, you'd be able to access all those LLMs (OpenAI compatible) on HF model pages and via OpenAI client libraries too! 💥

Go, play with it today: https://huggingface.co/blog/inference-providers-featherless

P.S. They're also bringing on more GPUs to support all your concurrent requests!

danielhanchen

posted an update 14 days ago

Post

1859

Mistral releases Magistral, their new reasoning models! 🔥
GGUFs to run: unsloth/Magistral-Small-2506-GGUF

Magistral-Small-2506 excels at mathematics and coding.

You can run the 24B model locally with just 32GB RAM by using our Dynamic GGUFs.

Xenova

posted an update 20 days ago

Post

4058

NEW: Real-time conversational AI models can now run 100% locally in your browser! 🤯

🔐 Privacy by design (no data leaves your device)
💰 Completely free... forever
📦 Zero installation required, just visit a website
⚡️ Blazingly-fast WebGPU-accelerated inference

Try it out: webml-community/conversational-webgpu

For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech

Powered by Transformers.js and ONNX Runtime Web! 🤗 I hope you like it!

3 replies

·

ariG23498

posted an update 20 days ago

Post

1437

🚨 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

·

danielhanchen

posted an update 22 days ago

Post

3248

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

PhilCulliton

authored 2 papers 26 days ago

Predicting Severe Sepsis Using Text from the Electronic Health Record

Paper • 1711.11536 • Published Nov 30, 2017

Gemma 2: Improving Open Language Models at a Practical Size

Paper • 2408.00118 • Published Jul 31, 2024 • 78

reach-vb

posted an update about 1 month ago

Post

3958

hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗

16 replies

·

PhilCulliton

authored a paper about 1 month ago

Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation

Paper • 2505.00612 • Published May 1 • 9

danielhanchen

posted an update about 2 months ago

Post

1951

💜 Qwen3 128K Context Length: We've released Dynamic 2.0 GGUFs + 4-bit safetensors!
Fixed: Now works on any inference engine and fixed issues with the chat template.
Qwen3 GGUFs:
30B-A3B: unsloth/Qwen3-30B-A3B-GGUF
235-A22B: unsloth/Qwen3-235B-A22B-GGUF
32B: unsloth/Qwen3-32B-GGUF

Read our guide on running Qwen3 here: https://docs.unsloth.ai/basics/qwen3-how-to-run-and-finetune

128K Context Length:
30B-A3B: unsloth/Qwen3-30B-A3B-128K-GGUF
235-A22B: unsloth/Qwen3-235B-A22B-128K-GGUF
32B: unsloth/Qwen3-32B-128K-GGUF

All Qwen3 uploads: unsloth/qwen3-680edabfb790c8c34a242f95

sanmikoyejo

authored a paper about 2 months ago

The Leaderboard Illusion

Paper • 2504.20879 • Published Apr 29 • 70

Xenova

posted an update about 2 months ago

Post

8155

Introducing the ONNX model explorer: Browse, search, and visualize neural networks directly in your browser. 🤯 A great tool for anyone studying Machine Learning! We're also releasing the entire dataset of graphs so you can use them in your own projects! 🤗

Check it out! 👇
Demo: onnx-community/model-explorer
Dataset: onnx-community/model-explorer
Source code: https://github.com/xenova/model-explorer

danielhanchen

posted an update 2 months ago

Post

5881

🦥 Introducing Unsloth Dynamic v2.0 GGUFs!
Our v2.0 quants set new benchmarks on 5-shot MMLU and KL Divergence, meaning you can now run & fine-tune quantized LLMs while preserving as much accuracy as possible.

Llama 4: unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
DeepSeek-R1: unsloth/DeepSeek-R1-GGUF-UD
Gemma 3: unsloth/gemma-3-27b-it-GGUF

We made selective layer quantization much smarter. Instead of modifying only a subset of layers, we now dynamically quantize all layers so every layer has a different bit. Now, our dynamic method can be applied to all LLM architectures, not just MoE's.

Blog with Details: https://docs.unsloth.ai/basics/dynamic-v2.0

All our future GGUF uploads will leverage Dynamic 2.0 and our hand curated 300K–1.5M token calibration dataset to improve conversational chat performance.

For accurate benchmarking, we built an evaluation framework to match the reported 5-shot MMLU scores of Llama 4 and Gemma 3. This allowed apples-to-apples comparisons between full-precision vs. Dynamic v2.0, QAT and standard iMatrix quants.

Dynamic v2.0 aims to minimize the performance gap between full-precision models and their quantized counterparts.

philschmid

posted an update 2 months ago

Post

3182

Gemini 2.5 Flash is here! We excited launch our first hybrid reasoning Gemini model. In Flash 2.5 developer can turn thinking off.

**TL;DR:**
- 🧠 Controllable "Thinking" with thinking budget with up to 24k token
- 🌌 1 Million multimodal input context for text, image, video, audio, and pdf
- 🛠️ Function calling, structured output, google search & code execution.
- 🏦 $0.15 1M input tokens; $0.6 or $3.5 (thinking on) per million output tokens (thinking tokens are billed as output tokens)
- 💡 Knowledge cut of January 2025
- 🚀 Rate limits - Free 10 RPM 500 req/day
- 🏅Outperforms 2.0 Flash on every benchmark

Try it ⬇️
https://aistudio.google.com/prompts/new_chat?model=gemini-2.5-flash-preview-04-17

1 reply

·

Xenova

posted an update 2 months ago

Post

2728

Reasoning models like o3 and o4-mini are advancing faster than ever, but imagine what will be possible when they can run locally in your browser! 🤯

Well, with 🤗 Transformers.js, you can do just that! Here's Zyphra's new ZR1 model running at over 100 tokens/second on WebGPU! ⚡️

Giving models access to browser APIs (like File System, Screen Capture, and more) could unlock an entirely new class of web experiences that are personalized, interactive, and run locally in a secure, sandboxed environment.

For now, try out the demo! 👇
webml-community/Zyphra-ZR1-WebGPU