ngquocvinh/K2-Horizon-7B-GGUF - Каталог нейросетей
Генерация текста

ngquocvinh/K2-Horizon-7B-GGUF

Добавлено:
ngquocvinh/K2-Horizon-7B-GGUF

☕ If this GGUF made your day easier, a coffee would make mine. Send a coffee ☕ I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work. K2-Horizon-7B is IFM’s 7B-core dense K2-Horizon reasoning model. The upstream model advertises a native 524,288-token context window and supports English, Chinese, coding, reasoning, long-context, and agentic workloads. See the official model card for the upstream serving stack, prompt conventions, reasoning settings, and evaluation protocol. Upstream K2-Horizon-7B benchmark results; image and scores are from the official model card. This is a quantization-only release. No training, fine-tuning, merging, or weight modification other than GGUF conversion and quantization was performed. The table below compares each published GGUF with the BF16 reference on a held-out WikiText pilot: eight chunks from wiki.test.raw and eight chunks from wiki.valid.raw, with a 4,096-token context and the same K2 llama.cpp runtime. Values are averaged across the two splits. Lower Mean KLD, ΔPPL, and RMS Δp, and higher Top-1 agreement, indicate closer next-token behavior to BF16. The BF16 reference mean PPL was…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: ngquocvinh
Теги: llama.cpp, gguf, k2-horizon, quantized, endpoints_compatible, imatrix, conversational
Лайков: 3  |  Загрузок: 686

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.