robolamp/AliceAI-Foundation-80B-A3B-Base-GGUF - Каталог нейросетей
Генерация текста

robolamp/AliceAI-Foundation-80B-A3B-Base-GGUF

Добавлено:
robolamp/AliceAI-Foundation-80B-A3B-Base-GGUF

GGUF port of yandex/AliceAI-Foundation-80B-A3B-Base: MoE, 80B total / 3B active parameters, tokenizer embedded in every file. This is a base model — no chat template, not instruction-tuned; it continues raw text. Requires a llama.cpp fork. The aliceai architecture is not in upstream llama.cpp; a stock build fails with unknown model architecture. Use robolamp/llama.cpp at commit 9a9ca8b`. This notice will be removed once the port lands upstream. UPD: now supports MTP, recommended —spec-draft-n-max for Q4 is 2, for Q8 use 3. ¹ Total variation distance between next-token distributions and an f32 reference on a held-out prompt set; lower is better. Measured on the full model for Q8_0, on a truncated probe for the other rows. The port itself matches the HF f32 reference within 3.48e-05 TVD (100% head). ² Share of mass-carrying tokens (p ≥ 0.01) whose top choice is identical. — Not published: Q3KM. Head overlap drops to 50% and greedy generation degenerates on some prompts. — No IQ / imatrix variants: no importance matrix exists for this model yet. — The tokenizer follows transformers, not the SentencePiece proto (they disagree on leading whitespace), via a new optional key…

Модальности:
Генерация текста


Задача: Генерация текста
Автор: robolamp
Теги: gguf, llama.cpp, moe, quantized, alice-ai, mtp, ru, en
Лайков: 3  |  Загрузок: 2,726

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.