> [!WARNING] > LEGACY V1 — SUPERSEDED BY THE V2 FAMILY > This repository is the original V1 TC distiller and includes its legacy GGUF > exports. It is kept for reproducibility and historical use. The current > generation is V2: the low/distiller V2 plus the Mid, High, and > XHigh transducer tiers. Do not use this V1 repository for new production > runs. > ⚠️ This is NOT a chat model. This is a trace-processing tool. > Its job is to take a long reasoning trace (multi-turn agentic rollout, > tool calls, verbose reasoning) and produce a condensed ThinkingCap-style > trace: a short + a definitive numbered answer. Feed it traces, > not conversation. The output is meant to be parsed and served as > training data, not read as a chatbot reply. A compact reasoning-trace translator that re-does verbose frontier-model rollouts in the ThinkingCap (TC) style: a short block plus a definitive, numbered answer — no meta-commentary, no loops, no wasted tokens. Built by distilling 1,985 curated traces generated by bottlecapai/ThinkingCap-Qwen3.6-27B over a multi-teacher corpus (Qwen3.8-Max, GLM-5.2, Kimi K3) from r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation, then fine-tuned into…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: Davd-b01
Теги: gguf, lfm2, reasoning, distillation, thinking-cap, chain-of-thought, trace-translation, condensed-thinking
Лайков: 4 | Загрузок: 2,007
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
