sometimesanotion
ยท
AI & ML interests
Agentic LLM services, model merging, finetunes, distillation
Recent Activity
reacted
to
sequelbox's
post
with ๐ฅ
3 days ago
Two new releases today!
Firstly, our new Raiden-Mini dataset, powered by DeepSeek's newest https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale model!
- A V3.2-Speciale reasoning showcase: the Raiden prompts test the model's creative, analytic, and general reasoning skills!
- HEAD TO HEAD: a comparison subset pits V3.2-Speciale against V3.2 with the same prompts, providing a direct look at each model's advantages!
Get the new Raiden-Mini dataset: https://huggingface.co/datasets/sequelbox/Raiden-Mini-DeepSeek-V3.2-Speciale
On the model side, we've also brought Shining Valiant 3 to Ministral 3!
- Science-reasoning: https://huggingface.co/datasets/sequelbox/Celestia3-DeepSeek-R1-0528 for physics, biology, chemistry, compsci, astronomy, Earth science, and information theory.
- AI to build AI: the https://huggingface.co/datasets/sequelbox/Mitakihara-DeepSeek-R1-0528 dataset for high-quality reasoning performance on AI, MLOps, math and CUDA, complex adaptive and agentic systems, cognition, logic, linguistics, simulation, knowledge management, and more!
- Creative reasoning and general chat performance supplemented with https://huggingface.co/datasets/sequelbox/Raiden-DeepSeek-R1
Get the newest SV3: https://huggingface.co/ValiantLabs/Ministral-3-14B-Reasoning-2512-ShiningValiant3
Esper 3.1 is available for Ministral 3 as well: https://huggingface.co/ValiantLabs/Ministral-3-14B-Reasoning-2512-Esper3.1
We're working hard on our next Big New Release, coming out in the next few weeks :)
Help support our releases, donations used for models and datasets: https://huggingface.co/spaces/sequelbox/SupportOpenSource
Open source matters. Fight for it with us.
with love and friendship,
allegra
reacted
to
sequelbox's
post
with ๐ฅ
9 days ago
NEW RELEASE: Esper 3.1 for Ministral 3 14b, 8b, and 3b!
- Esper is our full-stack, full-cycle coding, DevOps, and architecture specialist!
- Our newest, best DeepSeek technical datasets emphasize more challenging queries and tough real-world coding tasks across a variety of programming languages and development paradigms:
- Titanium 3 for coding and reasoning in DevOps and architecture: https://huggingface.co/datasets/sequelbox/Titanium3-DeepSeek-V3.1-Terminus
- Tachibana 3 for high-difficulty code production in a variety of topics and programming languages:
- https://huggingface.co/datasets/sequelbox/Tachibana3-Part1-DeepSeek-V3.1-Terminus
- https://huggingface.co/datasets/sequelbox/Tachibana3-Part2-DeepSeek-V3.2
- Mitakihara for MLOps, AI building, use, expertise, and research: https://huggingface.co/datasets/sequelbox/Mitakihara-DeepSeek-R1-0528
Get Esper 3.1 now in all 3 Ministral 3 sizes! (We recommend 14b for general use.)
14b: https://huggingface.co/ValiantLabs/Ministral-3-14B-Reasoning-2512-Esper3.1
8b: https://huggingface.co/ValiantLabs/Ministral-3-8B-Reasoning-2512-Esper3.1
3b: https://huggingface.co/ValiantLabs/Ministral-3-3B-Reasoning-2512-Esper3.1
We'll be bringing more models to Ministral soon, including Shining Valiant 3 :)
We're currently working hard on a big release in a new specialty - hoping to have that up on Valiant Labs before the end of the year! We'll keep pushing the boundaries of what personal-sized AI can do for you.
See our Experimental Reasoning models and open-source datasets: https://huggingface.co/sequelbox
Help us keep working for open source AI with a donation: https://huggingface.co/spaces/sequelbox/SupportOpenSource
with love,
allegra
Organizations
