need-for-speed (Need4Speed)

posted an update 5 days ago

Post

4,213

𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐢𝐧𝐠 🧬 𝐅𝐢𝐧𝐞𝐃𝐍𝐀: 𝐭𝐡𝐞 𝐛𝐞𝐬𝐭 𝐝𝐚𝐭𝐚𝐬𝐞𝐭 𝐭𝐨 𝐭𝐞𝐚𝐜𝐡 𝐚𝐧𝐲 𝐥𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐦𝐨𝐝𝐞𝐥 𝐃𝐍𝐀.
Training Qwen3-14B on it produces Carbon-X, the strongest open model on DNA benchmarks, on par with GPT-6.1 Sol.

It contains:
- Midtraining: 300B+ tokens of genomic sequences, papers and web pages mixing DNA with text
- SFT: 200K samples, from variant effect prediction to sequence question answering
- RL: 98K prompts with verifiable rewards

Data, models and the full recipe are open.
HuggingFaceBio/FineDNA

Enjoy this late Halloween treat! 🎃

5 replies

·

wenhuach

posted an update 2 months ago

Post

2,637

We experimentally support algorithm composition (e.g., --algs awq,signround or --algs hadamard,awq,signround) in AutoRound to improve accuracy of quantized models. We welcome any practical, deployable algorithms that are ready for real-world use. Feel free to submit a PR or leave a comment in Issues.

https://github.com/intel/auto-round/blob/main/docs/algorithm_combinations.md

wenhuach

posted an update 5 months ago

Post

4,633

🚀 We provide **free** hardware to quantize models at the [Intel Low Bit Open LLM Leaderboard]( Intel/low_bit_open_llm_leaderboard), currently supporting Pure RTN mode powered by AutoRound

⭐ If you find it useful, please consider starring the AutoRound project on [GitHub](https://github.com/intel/auto-round)!

9 replies

·

Haihao

authored a paper 11 months ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published Dec 4, 2025 • 17

wenhuach

authored a paper 11 months ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published Dec 4, 2025 • 17

wenhuach

posted an update 11 months ago

Post

3,020

🚀 SignRoundV2 for LLM quantization: PTQ-level cost, QAT-level accuracy — yes, even at 2 bits.

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs (2512.04746)

wenhuach

posted an update about 1 year ago

Post

329

🚀 AutoRound(https://github.com/intel/auto-round) is now supported by SGLang!

After integrations with TorchAO, Transformers, and VLLM, AutoRound-quantized models are now officially compatible with SGLang — bringing faster and more flexible deployment to your LLM workflows.

💡 We’ve also enhanced the RTN mode (--iters 0), cutting quantization costs significantly for low-resource users.

⭐ Star our repo and stay tuned for more exciting updates!

wenhuach

posted an update about 1 year ago

Post

1,779

AutoRound keeps evolving its LLM quantization algorithm! 🚀
After enhancing W2A16 quantization, we now offer a fast algorithm to generate mixed bits/data-type schemes (~2mins for 8B models), great for MXFP4 and W2A16.
Learn more: https://github.com/intel/auto-round/blob/main/docs/step_by_step.md#autoscheme

lvwerra

authored a paper about 1 year ago

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Paper • 2510.08697 • Published Oct 9, 2025 • 41

wenhuach

posted an update about 1 year ago

Post

431

AutoRound v0.7 is out! 🚀
This release includes enhanced algorithms for W2A16, NVFP4, and MXFP4, along with support for FP8 models as input.
👉 Check out the full details here: https://github.com/intel/auto-round/releases/tag/v0.7.0

wenhuach

posted an update over 1 year ago

Post

1,958

🚀 AutoRound(https://github.com/intel/auto-round) Now Supports GGUF Export & Custom Bit Settings!

We're excited to announce that AutoRound now supports:
✅ GGUF format export – for seamless compatibility with popular inference engines.
✅ Custom bit settings – tailor quantization to your needs for optimal performance.

Check out these newly released models:
🔹Intel/Qwen3-235B-A22B-Instruct-2507-gguf-q4km-AutoRound
🔹Intel/Qwen3-235B-A22B-Instruct-2507-gguf-q2ks-mixed-AutoRound
🔹Intel/Kimi-K2-Instruct-gguf-q2ks-mixed-AutoRound

Stay tuned! An even more advanced algorithm for some configurations is coming soon.

lvwerra

authored a paper over 1 year ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26, 2025 • 81

loubnabnl

authored a paper over 1 year ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5, 2025 • 65

zhentaoyu

authored a paper over 1 year ago

HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

Paper • 2503.18860 • Published Mar 24, 2025 • 6

wenhuach

posted an update over 1 year ago

Post

1,917

AutoRound(https://github.com/intel/auto-round) has been integrated into vLLM , allowing you to run AutoRound-formatted models directly in the upcoming release.

Beside, we strongly recommend using AutoRound to generate AWQ INT4 models, as AutoAWQ is no longer maintained and manually configuring new models is not trivial due to the need for custom layer mappings.

loubnabnl

posted an update over 1 year ago

Post

8,526

SmolVLM is now available on PocketPal — you can run it offline on your smartphone to interpret the world around you. 🌍📱

And check out this real-time camera demo by @ngxson , powered by llama.cpp:
https://github.com/ngxson/smolvlm-realtime-webcam
https://x.com/pocketpal_ai

6 replies

·

zhentaoyu

authored a paper over 1 year ago

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Paper • 2505.04512 • Published May 7, 2025 • 36

wenhuach

posted an update over 1 year ago

Post

1,950

AutoRound(https://github.com/intel/auto-round) has been integrated into Transformers, allowing you to run AutoRound-formatted models directly in the upcoming release. Additionally, we are actively working on supporting the GGUF double-quant format, e.g. q4_k_s, stay tuned!

https://huggingface.co/blog/autoround

lvwerra

authored a paper over 1 year ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7, 2025 • 213

loubnabnl

authored a paper over 1 year ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7, 2025 • 213

AI & ML interests

Team members 18

need-for-speed's activity