> Bugfix release on top of Nova-1-0.8B: pair-tuned to stop hallucinating tool calls on prompts that need a plain answer, clean XML termination, and the missing Apache-2.0 LICENSE file was added. — Base: HyperAiCorp/Nova-1-0.8B (f7b64ef) — Patch: LoRA r16/a16, lr 5e-5, 3 epochs, 241 rows (negatives-heavy: chat / facts / explain prompts that used to trigger fake tool calls, plus positive tool-call anchors across JSON, XML and plain-text protocols), merged into a standalone BF16 checkpoint — Architecture: unchanged Qwen35ForConditionalGeneration`, vision encoder preserved, vocab 248320, stock Transformers — drop-in replacement for 1.0 No regression (spot-checked): calcu Suite: 100 cases (EN+RU) — calculator (graded by safe evaluation, not string match), weather, translate, currency, timer, note, greetings/facts/explanations as negatives, 6 multi-step chains with tool history. Identical prompts on all checkpoints, greedy decoding. Reproduce: toolbench.py —model —out r.json. Identical 0-shot greedy protocol on both checkpoints, fixed seed, subsample of the…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: HardcoreAI
Теги: qwen3_5, image-text-to-text, tool-use, function-calling, assistant, instruction-tuning, qwen3.5, hyperai
Лайков: 3 | Загрузок: 242
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.