Post
204
NEW RELEASE: Esper 3.1 for the all-new Qwen 3.5 27b!
- 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: sequelbox/Titanium3-DeepSeek-V3.1-Terminus
- Tachibana 3 for high-difficulty code production in a variety of topics and programming languages:
- sequelbox/Tachibana3-Part1-DeepSeek-V3.1-Terminus
- sequelbox/Tachibana3-Part2-DeepSeek-V3.2
- Mitakihara for MLOps, AI building, use, expertise, and research: sequelbox/Mitakihara-DeepSeek-R1-0528
Get Esper 3.1 now for Qwen 3.5 27b: ValiantLabs/Qwen3.5-27B-Esper3.1
We're very excited to build on the new Qwen 3.5 - look for Shining Valiant, Guardpoint, and the rest of our crew coming soon!
We're also planning for new datasets with the upcoming Deepseek V4, including improved agentic and deep-thinking capabilities, and making use of Deepseek's architecture innovations!
See our Experimental Reasoning models and open-source datasets: @sequelbox
Help us keep working for open source AI with a donation - used directly for new models and datasets: sequelbox/SupportOpenSource
Fight for open source. It's an investment in your own future with AI. Closed-source providers will get more expensive, restrictive, and punitive in the long run if they win.
with love, your captain,
allegra
- 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: sequelbox/Titanium3-DeepSeek-V3.1-Terminus
- Tachibana 3 for high-difficulty code production in a variety of topics and programming languages:
- sequelbox/Tachibana3-Part1-DeepSeek-V3.1-Terminus
- sequelbox/Tachibana3-Part2-DeepSeek-V3.2
- Mitakihara for MLOps, AI building, use, expertise, and research: sequelbox/Mitakihara-DeepSeek-R1-0528
Get Esper 3.1 now for Qwen 3.5 27b: ValiantLabs/Qwen3.5-27B-Esper3.1
We're very excited to build on the new Qwen 3.5 - look for Shining Valiant, Guardpoint, and the rest of our crew coming soon!
We're also planning for new datasets with the upcoming Deepseek V4, including improved agentic and deep-thinking capabilities, and making use of Deepseek's architecture innovations!
See our Experimental Reasoning models and open-source datasets: @sequelbox
Help us keep working for open source AI with a donation - used directly for new models and datasets: sequelbox/SupportOpenSource
Fight for open source. It's an investment in your own future with AI. Closed-source providers will get more expensive, restrictive, and punitive in the long run if they win.
with love, your captain,
allegra