This is a sharded version of Meta’s Llama 2 chat 7b model, specifically the hugging face version. Shards are 5 GB max in size — intended to be loadable into free Google Colab notebooks. Colab notebook for sharding: https://colab.research.google.com/drive/1f1q9qc56wzB7-bjgNyLlO6f28ui1esQ Colab notebook for inference (just change the model id): https://colab.research.google.com/drive/1zxwaTSvd6PSHbtyaoa7tfedAS31jN6m Get started by saving your own copy of this fLlama_Inference notebook. You will be able to run inference using a free Colab notebook if you select a gpu runtime. See the notebook for more details. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom. Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Trelis
Теги: llama, facebook, meta, llama-2, sharded, en, text-generation-inference
Лайков: 3 | Загрузок: 12
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
