AnkitAI/Parable-Nanbeige4.2-3B-Claude-Fable-5 - Каталог нейросетей
Генерация текста

AnkitAI/Parable-Nanbeige4.2-3B-Claude-Fable-5

Добавлено:
AnkitAI/Parable-Nanbeige4.2-3B-Claude-Fable-5

Part of the Parable series: small local LLMs fine-tuned on genuine agent traces. This is the reasoning-style chat variant of Nanbeige4.2-3B (to our knowledge the first published fine-tune of this base), tuned on real Claude Fable 5 agent transcripts so its step-by-step reasoning voice carries into local use. GGUF quants for llama.cpp / Ollama / LM Studio: Parable-Nanbeige4.2-3B-Claude-Fable-5-GGUF trustremotecode=True is required: the architecture ships its own modeling code (modelingnanbeige.py`, included in this repo). Note usecache=False: the base architecture’s modeling code was written against transformers 4.42 and calls a cache API that transformers removed in later versions, so cached generation crashes with ‘DynamicCache’ object has no attribute ‘getmaxlength’ on transformers 4.47+. Either pass usecache=False (shown above, slower) or pin transformers>=4.42, Output begins with a … reasoning block, then the answer. If you are building on top of this model, parse and strip the think block before showing text to end users. The architecture runs its 22-layer stack twice (numloops: 2`, effective depth 44). This is encoded in the GGUF and handled automatically; expect roughly…

Модальности:
Генерация текста

Области применения:
Генерация кода Логика и рассуждение Диалог / чат


Задача: Генерация текста
Автор: AnkitAI
Теги: nanbeige, qlora, agentic, coding, reasoning, conversational, custom_code
Лайков: 4  |  Загрузок: 167

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.