sequelbox/Tachibana4-DeepSeek-V4-Pro
Viewer • Updated • 17.2k • 4
t.d.a.g. PRO
sequelbox
AI & ML interests
open source, infinite games. (they/them)
Recent Activity
posted an update about 4 hours ago
JUST RELEASED: the Tachibana 4 DeepSeek-V4-Pro dataset and our all-new Tachibana-Agent coding model!
- Questions prioritize real-world, challenging agentic coding tasks across a variety of programming languages and topics. Synthetic prompts utilize a variety of personas, experience levels, and styles of communication to maximize real-world flexibility and usability.
- Areas of focus include back-end and front-end development, systems programming, distributed systems, performance optimization, data structures, databases and data engineering, game and mobile development, security engineering, compiler design, custom tooling, task automation, practical bugfixes, and more!
- A wide variety of emphasized languages improves development capability: Python, C, C++, C#, Go, TypeScript, Java, JavaScript, Rust, Haskell, SQL, Shell, R, Ruby, assembly code, and more!
The new dataset: https://huggingface.co/datasets/sequelbox/Tachibana4-DeepSeek-V4-Pro
The new model: https://huggingface.co/sequelbox/Qwen3.6-27B-Tachibana-Agent
We're thrilled to bring this to everyone - try it out and see what you think!
Tachibana 4 is the first of several datasets used for the upcoming Esper 4! See what we're working on and help our releases come out faster: https://huggingface.co/spaces/sequelbox/SupportOpenSource
Open source will win :)
love,
allegra liked a model about 4 hours ago
sequelbox/Qwen3.6-27B-Tachibana-Agent updated a model about 4 hours ago
sequelbox/Qwen3.6-27B-Tachibana-AgentOrganizations
