Original model: https://huggingface.co/qingy2024/QwQ-14B-Math-v0.2 Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: You can either specify a new local-dir (QwQ-Unofficial-14B-Math-v0.2-Q8_0) or download them all in place (./) Previously, you would download Q4044/48/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. Now, however, there is something called «online repacking» for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. As of llama.cpp build b4282 you will not be able to run the Q40XX files and will instead need to use Q40. Additionally, if you want to get slightly better quality for , you can use IQ4NL thanks to this PR which will also repack the weights for ARM, though only the 44 for now. The loading time may be slower…
Модальности:
Генерация текста
Области применения:
Диалог / чат Математика
Задача: Генерация текста
Автор: bartowski
Теги: gguf, text-generation-inference, unsloth, qwen2, trl, sft, en, endpoints_compatible
Лайков: 4 | Загрузок: 889
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
