Alternatives
Products that do what Ölchen does
Distillation knowledge - precise, understandable, applicable
- 1DD
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Jul 2026 · ctgt.ai
- 2
- 3
- 4
- 5AF
I’ve loved keeping plants since I was a kid. But the online world of plants can be confusing - strange vocabulary, plants going by conflicting names, and hundreds of niche websites. I wanted to create a site that would organize all of this info and make it easier to explore and discover new plants. That’s why I created GetAnyPlant, which aggregates and matches plants from dozens of online stores. It includes huge amounts of data on these plants along with filters and categories to help you search. You can also save plants to your wishlist and add notes to them. I’m a data scientist by…
2024 · getanyplant.com
- 6
- 7
- 8
- 9
- 10
- 11DA
Over the past few months, I have built a distillation toolkit that supports cross-tokenizer distillation (e.g., distilling from LLaMA to Qwen vocab, or others). This approach has worked well on reasoning datasets like AIME, and we’ve validated on models like Phi and Qwen. We’ve also integrated Modal for quick deployment (with $30/month credits to try it out). Would love any feedback! GitHub: https://github.com/agokrani/distillKitPlus Docs: https://distillkitplus.mintlify.app/
2025 · github.com
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →