# ThakiCloud: Open-Weight Models and Datasets Source: https://savrn.com/model-publishers/thakicloud Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Models Model · Text ranking ### [SKILLRET-Reranker-0.6B](https://savrn.com/models/skillret-reranker-0-6b-2) [ThakiCloud](https://savrn.com/model-publishers/thakicloud) This is a reranker fine-tuned for AI agent skill retrieval. Given a natural-language user request and a candidate agent skill, it scores how relevant and useful the skill is for the request. It is designed as the second stage after a first-stage retriever such as SkillRet-Embedding-0.6B or SkillRet-Embedding-8B. The model is fine-tuned from Qwen/Qwen3-Reranker-0.6B on the SkillRet benchmark training split with binary cross-entropy on the yes/no token probability. It keeps the scoring interface of Qwen3-Reranker. Technical report: SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents (arXiv:2605.05726) Each skill document is body, the same representation used by the SkillRet… Open weights apache-2.0 596M parameters 40,960 tokens transformers [View model](https://savrn.com/models/skillret-reranker-0-6b-2) Model · Image and text to text ### [Qwen3.8-27B-Human-KO-Enterprise-Boundary](https://savrn.com/models/qwen3-8-27b-human-ko-enterprise-boundary) [ThakiCloud](https://savrn.com/model-publishers/thakicloud) Enterprise policy decision model — Korean-supervised, zero-shot English. The boundary-targeted checkpoint from When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned? Merged full weights — not an adapter — with the pointer head shipped alongside. It decides which one of seven actions an enterprise agent should take under a written policy, before any text is generated: trained on contrastive boundary pairs — records differing in one decision-relevant factor across three boundaries (answer vs. call a tool, call a tool vs. ask for confirmation, missing information) — against a control given the same number of tokens of randomly sampled in-domain data. Data was the… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-8-27b-human-ko-enterprise-boundary) ## Datasets Dataset · Text classification ### [EnterpriseOps-KO-Blind-A](https://savrn.com/datasets/enterpriseops-ko-blind-a) [ThakiCloud](https://savrn.com/model-publishers/thakicloud) A sealed Korean benchmark of 300 enterprise policy decisions whose gold labels were computed, not written. No human and no language model ever supplied an answer. A hidden executable policy maps a set of latent factors to exactly one correct action and emits a proof; the natural-language rendering is produced separately and never sees the label. Each item asks the same question an enterprise agent has to answer before it says anything: given this written policy, these callable tools, what the system already knows, and this user turn — which one of seven actions is correct? the usual routes first and they failed, which is why this one exists. So the boundary is no longer written into the… Publicly accessible cc-by-4.0 n<1K [View dataset](https://savrn.com/datasets/enterpriseops-ko-blind-a) ## Explore More - [All model publishers](https://savrn.com/model-publishers) - [The model directory](https://savrn.com/models) - [The dataset directory](https://savrn.com/datasets) ## Source - Listed from their public repositories, read 2026-09-25. - [Hugging Face profile](https://huggingface.co/ThakiCloud) - [How the hub is built](https://savrn.com/model-hub/methodology)