allegra

ValiantLabs/Qwen3-8B-ShiningValiant3 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Shining Valiant 3 :) huggingface.co/ValiantLabs/...

cobalt 2 coming soon. we have models to build

ValiantLabs/Qwen3-8B-Esper3 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

esper 3 is here :) coding, architecture, DevOps, creative reasoning, general chat. Get it on HF: huggingface.co/ValiantLabs/...

sneak preview is now up on HF!

Tachibana 2 coming ASAP :) using deepseek r1 :) for everyone

Raiden-Deepseek-R1 is here! A deep-dive dataset into the creative, analytic, and reasoning capabilities of Deepseek's R1 model. Available on @hf.co for everyone: huggingface.co/datasets/seq...

next R1 reasoning dataset after Raiden is technical as well. Seems like the type of thing you'd see a new model release along with :) coming soon!

sequelbox/Raiden-DSR1-PREVIEW · Datasets at Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

New sneak peek at my first dataset with Deepseek's excellent 685b R1 model - Raiden uses creative and analytical prompts to challenge R1's reasoning skills. For everyone to use: huggingface.co/datasets/seq...

cool, excited to try it out! glad to see apache license :)

upcoming Deepseek-R1 datasets: creative-reasoning and code-reasoning first. SV3 datasets will come too! love what I've seen so far

very impressed with the new deepseek release + distilled versions! Datasets coming soon :)

deepseek-ai (DeepSeek) Org profile for DeepSeek on Hugging Face, the AI community building the future.

BIG release by DeepSeek AI🔥🔥🔥

DeepSeek-R1 & DeepSeek-R1-Zero: two 660B reasoning models are here, alongside 6 distilled dense models (based on Llama & Qwen) for the community!
huggingface.co/deepseek-ai
huggingface.co/deepseek-ai/...

more QVQ datasets on the way soon! The next dataset release uses creative-generalist reasoning prompts.

sequelbox/Tachibana-QVQ · Datasets at Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Tachibana-QVQ is here! Code-reasoning and code-instruct data generated by Qwen's QVQ 72b model. Get it now on @hf.co at huggingface.co/datasets/seq...

sequelbox/Tachibana-QVQ-PREVIEW · Datasets at Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Check out the new preview release of Tachibana-QVQ: code-reasoning data created by Qwen's new QVQ-72B-Preview model! Take a look at QVQ's coding ability: huggingface.co/datasets/seq...

* Blog: qwenlm.github.io/blog/qvq-72b...
* HF: huggingface.co/collections/...
* ModelScope: modelscope.cn/models/Qwen/...
* Kaggle: kaggle.com/models/qwen-...
* Demo: huggingface.co/spaces/Qwen/...

Excited to compare it to QwQ 32b!

Find my open-source datasets on @hf.co, including science-instruct, code-instruct, DevOps, general chat, multi-turn and more! For everyone to use. More to come soon!