Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU. Checkpoint compatible to ctranslate2>=3.17.1 and hf-hub-ctranslate2>=2.12.0 — computetype=int8float16 for device=»cuda» — computetype=int8 for device=»cpu»` This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo. Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 34B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom. To use this model, please make sure to install transformers from main until the next version is released: — [x] Code completion. — [ ] Infilling. — [ ] Instructions / chat. — [ ] Python specialist. *Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs). Variations Code Llama comes in three model sizes, and three variants: Code Llama: base models designed for general code synthesis…
Модальности:
Генерация текста
Области применения:
Генерация кода
Задача: Генерация текста
Автор: michaelfeil
Теги: llama, ctranslate2, int8, float16, llama-2, code, endpoints_compatible
Лайков: 2 | Загрузок: 37
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
