gg-tt (gg-tt)

Xenova

posted an update about 5 hours ago

Post

283

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 3 days ago

Post

5429

🦥 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 10 days ago

Post

2221

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 12 days ago

Post

2480

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

1 reply

·

tomaarsen

posted an update 13 days ago

Post

2672

I just released Sentence Transformers v4.1; featuring ONNX and OpenVINO backends for rerankers offering 2-3x speedups and improved hard negatives mining which helps prepare stronger training datasets. Details:

🏎️ ONNX, OpenVINO, Optimization, Quantization
- I've added ONNX and OpenVINO support with just one extra argument: "backend" when loading the CrossEncoder reranker, e.g.: CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2", backend="onnx")
- The export_optimized_onnx_model, export_dynamic_quantized_onnx_model, and export_static_quantized_openvino_model functions now work with CrossEncoder rerankers, allowing you to optimize (e.g. fusions, gelu approximations, etc.) or quantize (int8 weights) rerankers.
- I've uploaded ~340 ONNX & OpenVINO models for all existing models under the cross-encoder Hugging Face organization. You can use these without having to export when loading.

⛏ Improved Hard Negatives Mining
- Added 'absolute_margin' and 'relative_margin' arguments to mine_hard_negatives.
- absolute_margin ensures that sim(query, negative) < sim(query, positive) - absolute_margin, i.e. an absolute margin between the negative & positive similarities.
- relative_margin ensures that sim(query, negative) < sim(query, positive) * (1 - relative_margin), i.e. a relative margin between the negative & positive similarities.
- Inspired by the excellent NV-Retriever paper from NVIDIA.

And several other small improvements. Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v4.1.0

With this release, I introduce near-feature parity between the SentenceTransformer embedding & CrossEncoder reranker models, which I've wanted to do for quite some time! With rerankers very strongly supported now, it's time to look forward to other useful architectures!

pcuenq

authored a paper 20 days ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 21 days ago • 176

Xenova

authored a paper 20 days ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 21 days ago • 176

reach-vb

authored a paper 20 days ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 21 days ago • 176

sanmikoyejo

authored a paper 21 days ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 21 days ago • 99

danielhanchen

posted an update 21 days ago

Post

4818

You can now run Llama 4 on your own local device! 🦙
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF

You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4

1 reply

·

RyanMullins

authored a paper 25 days ago

ShieldGemma 2: Robust and Tractable Image Content Moderation

Paper • 2504.01081 • Published 27 days ago • 3

danielhanchen

posted an update 29 days ago

Post

3438

You can now run DeepSeek-V3-0324 on your own local device!
Run our Dynamic 2.42 and 2.71-bit DeepSeek GGUFs: unsloth/DeepSeek-V3-0324-GGUF

You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-v3-0324-locally