— measurement.json — 3.0bpw — 4.0bpw — 5.0bpw — 6.0bpw — 8.0bpw This is the second in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Qwen1.5 32B. Model has been Instruct tuned with the ChatML formatting. A typical input would look like this: Three new general purpose instruction following datasets were added on top of the original Stheno dataset (which had certain low quality entries purged/removed). The first two were designed specifically for the Magnum series, to better address prompt adherence and coherence: — kalomaze/OpusInstruct25k — Nopm/Opus_WritingStruct — Gryphe/Sonnet3.5-SlimOrcaDedupCleaned (A ~16k rows subset) This model has been a team effort, and the credits goes to all members of Anthracite. The training was done for 2 epochs with a learning rate of 1e-05. We used 8x NVIDIA H100 Tensor Core GPUs for the full-parameter fine-tuning of the model.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: anthracite-org
Теги: chat, en, zh
Лайков: 3 | Загрузок: 2
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
