Opus-forward delta merge anchored to Qwen3.5-9B, keeping Fable tool-use behavior while biasing toward the high-performance Opus reasoning family. This is a bf16 safetensors merge in the Qwen3.5-9B family. It combines the agentic/tool-use flavor of Fable 5 distillation with Claude Opus reasoning distilled checkpoints. — Base anchor: Qwen/Qwen3.5-9B — Merge method: deltalinear — Output dtype: bfloat16` Weights: — empero-ai/Qwable-9B-Claude-Fable-5: 0.38 — Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled: 0.42 — Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2: 0.2 The local mergekit/transformers stack did not yet recognize the new qwen35` model type, so the merge was performed directly tensor-by-tensor over compatible safetensors checkpoints. Non-floating tensors are copied from the Fable/Qwable checkpoint; floating tensors are emitted as bf16. — Fable source: empero-ai/Qwable-9B-Claude-Fable-5, derived from Fable 5 traces. — Opus source: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled, a high-download Opus reasoning distilled checkpoint. — Opus v2 source: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2. General chat, code assistance, tool-use…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: bingleai
Теги: qwen3_5, image-text-to-text, qwen, qwen3.5, fable-5, claude-opus, distillation, merge
Лайков: 3 | Загрузок: 21
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
