Merged version of IFM/K2-Horizon-7B-Uno, a diffusion-augmented LLM based on K2-Horizon-7B. This repository contains the LoRA adapter merged directly into the base model weights using PyTorch + PEFT, so it runs as a standard autoregressive model without needing the custom Ψ-Spec sampler. Upstream model: IFM/K2-Horizon-7B-Uno by Institute of Foundation Models, released under Apache 2.0. Conversion: Merged using PyTorch + PEFT, validated with text generation, then quantized to MLX format using Hermes Agent. — AR pathway: Standard K2-Horizon-7B weights (next-token prediction) — Diffusion pathway: LoRA-based diffusion adapters (merged into AR weights) K2-Horizon-7B is a reasoning model. Always use reasoningeffort=»high»`: K2-Horizon requires oMLX v0.6.4+ with the K2-Horizon support patch: — Registers k2horizon model type — Recognizes IFM thinking tags (, , ) — Parses IFM tool call format (, , ) — Strips tags in streaming and non-streaming paths
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: hermitdave
Теги: mlx, k2_horizon, apple-silicon, uno, merged, conversational, custom_code
Лайков: 3 | Загрузок: 258
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
