Original Model: facebook/llm-compiler-13b Original dtype: BF16 (bfloat16) Quantized by: llama.cpp b3256 IMatrix dataset: here — Files — IMatrix — Common Quants — All Quants — Downloading using huggingface-cli — Inference — Llama.cpp — FAQ — Why is the IMatrix not applied everywhere? — How do I merge a split GGUF? —— | ———- | ——— | —— | ———— | ——— | If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results). 1. Make sure you have gguf-split available — To get hold of gguf-split, navigate to https://github.com/ggerganov/llama.cpp/releases — Download the appropriate zip for your system from the latest release — Unzip the archive and you should be able to find gguf-split 2. Locate your GGUF chunks folder (ex: llm-compiler-13b.Q80) 3. Run gguf-split —merge llm-compiler-13b.Q80/llm-compiler-13b.Q80-00001-of-XXXXX.gguf llm-compiler-13b.Q80.gguf — Make sure to point gguf-split to the first chunk of the split.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: legraphista
Теги: gguf, quantized, GGUF, quantization, imat, imatrix, static, 16bit
Лайков: 3 | Загрузок: 1,291
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
