Using llama.cpp commit b5e9546 for quantization, featuring llama 3.1 rope scaling factors. This fixes low-quality issues when using 8-128k context lengths. Original model: https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct All quants were made using the imatrix option and Bartowski’s calibration file. The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks. Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. Training Data Params Input modalities Output modalities Context length GQA Token count Knowledge cutoff Llama 3.1 (text only) A new mix of publicly available online data. 8B …
Модальности:
Генерация текста
Области применения:
Диалог / чат Следование инструкциям
Задача: Генерация текста
Автор: ThomasBaruzier
Теги: gguf, facebook, meta, llama, llama-3, en, de, fr
Лайков: 3 | Загрузок: 3,433
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
